© 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
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7803
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Philip."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.61
    tagPool
    -0.60
    //
    -0.60
    mybatisplus
    -0.57
    principalTable
    -0.52
    ftagPool
    -0.52
     groupBox
    -0.50
    XmlAccessorType
    -0.50
    ArgsConstructor
    -0.49
    jooq
    -0.49
    POSITIVE LOGITS
     Phil
    0.57
     PHIL
    0.51
    Phil
    0.51
    PHIL
    0.51
     Фили
    0.48
    phil
    0.47
     phil
    0.43
    Fili
    0.42
     Fili
    0.39
    omena
    0.39
    Activations Density 0.206%

    No Known Activations