© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9012
    Prev
    Next
    INDEX
    Explanations

    references to celebrity and tax-related issues

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

    source citations and attributions in text (phrases like "a source said," "an insider told," "via," "photo by," etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.42
     `/
    -0.37
     therefor
    -0.36
    AnchorTagHelper
    -0.36
     sair
    -0.35
     protoimpl
    -0.35
     HasFactory
    -0.35
    引用元
    -0.35
     cinza
    -0.35
     Whilst
    -0.34
    POSITIVE LOGITS
    PHOTOS
    0.52
     EW
    0.45
    ThroughAttribute
    0.45
    ########.
    0.45
    zzini
    0.45
    :+:
    0.44
    DataContract
    0.44
    Становништво
    0.42
     PHOTOS
    0.42
     ModelRenderer
    0.42
    Activations Density 0.179%

    No Known Activations