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. 17-GEMMASCOPE-RES-16K
    6. 9182
    Prev
    Next
    INDEX
    Explanations

    key events and actions occurring in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.59
    ellido
    -0.54
     cherchés
    -0.52
    országban
    -0.50
    woord
    -0.49
    iligung
    -0.49
     بتاريخ
    -0.48
    Sklici
    -0.47
    Controller
    -0.47
    pley
    -0.47
    POSITIVE LOGITS
     reinstate
    0.54
     venter
    0.54
     reinstatement
    0.51
     Eastman
    0.51
     penalty
    0.50
    istungen
    0.50
     CITES
    0.50
     administered
    0.49
     Poto
    0.49
    httphttps
    0.48
    Activations Density 0.070%

    No Known Activations