© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6550
    Prev
    Next
    INDEX
    Explanations

    phrases related to consent and the ability to withdraw from agreements or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    language expressing the ability to terminate, withdraw, or change something at any time.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    language about the ability to revoke, withdraw, change, or remove something at any time.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language granting permission, ability, or rights to change settings or withdraw/opt out (e.g., end participation) at any time.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.49
    featureID
    -0.48
     possibili
    -0.47
    المشاركات
    -0.46
    orianCalendar
    -0.44
    
    -0.44
    urlpatterns
    -0.43
     محفوظة
    -0.42
    なぜか
    -0.42
     lest
    -0.42
    POSITIVE LOGITS
     anytime
    1.65
     any
    1.35
     whatever
    1.32
     whichever
    1.30
     anywhere
    1.28
     Anytime
    1.20
    whatever
    1.17
     cualquier
    1.16
    Anytime
    1.15
     ANY
    1.14
    Activations Density 0.735%

    No Known Activations