© 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. 5-GEMMASCOPE-RES-16K
    11. 10758
    Prev
    Next
    INDEX
    Explanations

    references to IDs, particularly in coding and data management contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.02
     Krav
    -0.89
    inalg
    -0.89
    <h6>
    -0.88
    InvalidProtocol
    -0.88
    itemID
    -0.87
     beginnetje
    -0.85
     Rota
    -0.83
    GraphicsUnit
    -0.82
    DNEY
    -0.82
    POSITIVE LOGITS
    Id
    1.53
     Id
    1.29
    fileId
    1.04
    cityId
    0.95
    Ids
    0.94
     Idris
    0.92
     getId
    0.91
    mId
    0.87
    getId
    0.86
     Idy
    0.85
    Activations Density 0.097%

    No Known Activations