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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 119800
    Prev
    Next
    INDEX
    Explanations

    directives and recommendations in communication

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

    guide or instruction

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences or phrases giving instructions, advice, or directives (imperative/modal directive language).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.53
     Diſ
    -0.49
     Inſ
    -0.47
     raiſ
    -0.47
     Conſ
    -0.46
     viſ
    -0.44
    queryInterface
    -0.44
     itſelf
    -0.44
     UIAlert
    -0.43
     Chriftian
    -0.43
    POSITIVE LOGITS
     فق
    0.41
    isAuth
    0.39
    gili
    0.38
    ilier
    0.37
     bluff
    0.36
    esco
    0.36
    stadt
    0.36
    arası
    0.36
    irem
    0.36
    accia
    0.36
    Activations Density 0.302%

    No Known Activations