Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8576
    Prev
    Next
    INDEX
    Explanations

    specific programming and coding constructs related to data processing and context management

    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
    /*
    -0.51
    aparte
    -0.50
    </strong>
    -0.48
     estekak
    -0.48
    MarshalTo
    -0.47
     viol
    -0.47
     olsun
    -0.43
    LikeLike
    -0.43
    DoubleQuotes
    -0.42
     distanciation
    -0.42
    POSITIVE LOGITS
     мәкал
    0.78
     <=",
    0.71
    __*/
    0.70
    Hauptartikel
    0.70
    tableFuture
    0.66
    )++;
    0.65
    sizeCache
    0.64
     Dostupné
    0.61
    OGND
    0.61
    MENAFN
    0.61
    Activations Density 0.693%

    No Known Activations