© 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. 470
    Prev
    Next
    INDEX
    Explanations

    references to unique identifiers or IDs in a technical context

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

    references to identifiers and IDs in a technical context

    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
    celotti
    -0.82
     "]
    -0.79
    endola
    -0.78
    OrEqual
    -0.76
     !!}
    -0.76
    */}
    -0.75
     AOS
    -0.73
    WithIOException
    -0.73
     ...]
    -0.73
    brtc
    -0.72
    POSITIVE LOGITS
     ID
    1.27
    ID
    1.23
     getID
    1.15
    itemID
    1.07
    ByID
    1.05
     userID
    1.03
    IDs
    0.98
    userID
    0.98
     IDs
    0.97
    getID
    0.96
    Activations Density 0.053%

    No Known Activations