© 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. 3805
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of futility

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

    phrases expressing ineffectiveness or lack of impact, particularly the pattern "do/does nothing to [verb]".

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

    phrases expressing ineffectiveness or lack of action, particularly "do/does nothing" and "do/does anything".

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

    mentions of indefinite pronouns referring to nonspecific things, often in “do/does …” constructions indicating (lack of) action or effect.

    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
     betweenstory
    -0.28
     terv
    -0.26
    jadikan
    -0.26
    weitere
    -0.25
    rokken
    -0.25
     हुई
    -0.25
     होने
    -0.24
    CardHeader
    -0.24
     memberikan
    -0.24
     EN
    -0.24
    POSITIVE LOGITS
     queſta
    0.76
     PeEnEo
    0.68
     juſ
    0.66
    pexpr
    0.66
    DispatchToProps
    0.65
     faſt
    0.64
     againſt
    0.63
     للاسماء
    0.62
    ſelves
    0.62
    ſelf
    0.61
    Activations Density 0.173%

    No Known Activations