© 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. 50244
    Prev
    Next
    INDEX
    Explanations

    pronouns, specifically those referring to the second and third person

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

    or clauses with pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    essive
    -0.44
    >\<^
    -0.43
    \<^
    -0.42
    тс
    -0.42
    wahati
    -0.42
    genöss
    -0.40
     juſ
    -0.40
    mband
    -0.39
     isoto
    -0.39
     Penga
    -0.39
    POSITIVE LOGITS
     or
    0.82
     hoặc
    0.70
     또는
    0.68
     oppure
    0.64
     или
    0.63
     eller
    0.62
    または
    0.62
     nebo
    0.62
     Or
    0.61
    それとも
    0.60
    Activations Density 0.009%

    No Known Activations