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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 11794
    Prev
    Next
    INDEX
    Explanations

    terms related to data fetching operations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milner
    -0.95
    rekli
    -0.86
     baseman
    -0.76
     Paredes
    -0.72
    CardContent
    -0.71
    достатки
    -0.70
    gros
    -0.70
    oquia
    -0.67
    PAN
    -0.67
    ئيس
    -0.66
    POSITIVE LOGITS
     FETCH
    1.53
    FetchType
    1.45
     Fetch
    1.45
     fetch
    1.44
    fetch
    1.41
    FETCH
    1.30
    Fetch
    1.25
     fetched
    1.11
    Fetcher
    1.08
     fetching
    1.06
    Activations Density 0.050%

    No Known Activations