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. 25-GEMMASCOPE-RES-16K
    6. 12460
    Prev
    Next
    INDEX
    Explanations

    references to statistical methods and their authors in the context of causal inference models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whole
    -0.45
     or
    -0.45
    PreferredItem
    -0.45
     Connectez
    -0.44
    췄
    -0.43
     GeoNames
    -0.43
     college
    -0.43
     community
    -0.43
     big
    -0.43
     peggio
    -0.43
    POSITIVE LOGITS
    findpost
    0.68
    Przypisy
    0.64
    談社
    0.64
    writel
    0.64
     eds
    0.63
    Източници
    0.60
    )].
    0.60
    dataTables
    0.58
    WebMethod
    0.58
    )}.
    0.55
    Activations Density 0.191%

    No Known Activations