© 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. 3-GEMMASCOPE-RES-16K
    11. 9847
    Prev
    Next
    INDEX
    Explanations

    instances of the address-of operator and references to memory addresses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.82
     незавершена
    -0.78
     betweenstory
    -0.75
    ніципалі
    -0.73
    "]();
    -0.73
    providedIn
    -0.72
     continuant
    -0.72
    WebElementEntity
    -0.70
     Италијани
    -0.68
     :}
    -0.68
    POSITIVE LOGITS
     Manajemen
    0.64
    vice
    0.64
    êmica
    0.58
    čenje
    0.57
    [++
    0.56
     Penny
    0.56
     Mounted
    0.54
    struzioni
    0.53
    enumi
    0.53
     suprême
    0.53
    Activations Density 0.290%

    No Known Activations