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. 10-GEMMASCOPE-RES-16K
    6. 4615
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blessés
    -0.63
    CSRF
    -0.58
    fois
    -0.57
     secondaires
    -0.56
     Obrigado
    -0.56
    enderror
    -0.55
     émotion
    -0.55
    🦱
    -0.54
     licorne
    -0.54
     construite
    -0.54
    POSITIVE LOGITS
    matchCondition
    0.95
    RectangleBorder
    0.91
     NgModule
    0.89
     TestBed
    0.79
     ModelExpression
    0.74
    AlterField
    0.71
    NgModule
    0.69
    TestBed
    0.68
    +#+
    0.67
     članak
    0.67
    Activations Density 0.019%

    No Known Activations