Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8688
    Prev
    Next
    INDEX
    Explanations

    emotional responses and interactions between characters, particularly involving expressions of affection or embarrassment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.76
    出版年
    -0.72
    StructEnd
    -0.69
    </tfoot>
    -0.67
    下载附件
    -0.65
    DeleteBehavior
    -0.62
    ಂದ
    -0.62
    offsetof
    -0.62
    migrationBuilder
    -0.62
    sonian
    -0.62
    POSITIVE LOGITS
    tagHelperRunner
    0.71
     Clifton
    0.48
    脚注の使い方
    0.47
     ließ
    0.45
    KeySpec
    0.44
    Rè
    0.43
    ListModule
    0.41
    ThroughAttribute
    0.41
     Rtl
    0.40
    ConstraintMaker
    0.39
    Activations Density 0.106%

    No Known Activations