© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 14815
    Prev
    Next
    INDEX
    Explanations

    details about strengths and weaknesses in personal or professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MessageBoxIcon
    -0.59
    IsPostBack
    -0.52
     MaterialApp
    -0.50
    JpaRepository
    -0.50
    hmac
    -0.50
     isKindOfClass
    -0.48
    libft
    -0.48
    MigrationBuilder
    -0.47
     grà
    -0.47
     confirmé
    -0.47
    POSITIVE LOGITS
     weaknesses
    0.64
     strengths
    0.60
     strategies
    0.60
     noqa
    0.56
     areas
    0.56
     opportunities
    0.54
     practices
    0.54
    Strengths
    0.54
    niest
    0.53
    principalTable
    0.52
    Activations Density 0.290%

    No Known Activations