© 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. 30-GEMMASCOPE-RES-16K
    11. 12212
    Prev
    Next
    INDEX
    Explanations

    conversational phrases that highlight emotional states and interpersonal dynamics

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

    "already"

    np_acts-logits-general · gemini-2.0-flash

    already has happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtext
    -0.36
     Administrativna
    -0.35
    次回は
    -0.34
     ulang
    -0.32
    gdx
    -0.31
     Infórmanos
    -0.30
    𝟹
    -0.30
    moires
    -0.30
    gartner
    -0.30
    getJSONArray
    -0.29
    POSITIVE LOGITS
     already
    4.09
    already
    3.69
     Already
    3.69
    Already
    3.55
     ALREADY
    3.17
     이미
    2.81
     уже
    2.81
     allerede
    2.75
     redan
    2.73
    ALREADY
    2.70
    Activations Density 1.525%

    No Known Activations