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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10674
    Prev
    Next
    INDEX
    Explanations

    references to the document object in JavaScript code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.57
    críbete
    -0.56
    SizeMode
    -0.54
     referenties
    -0.54
    Albania
    -0.52
     buty
    -0.52
    lowy
    -0.51
    rrggbb
    -0.50
     Hins
    -0.49
     nämlich
    -0.48
    POSITIVE LOGITS
     cherchés
    0.58
     MonoBehaviour
    0.56
     >=",
    0.56
    hyrchwyd
    0.54
     estekak
    0.52
    UserScript
    0.51
    InstanceState
    0.50
     Preferencias
    0.49
    RetentionPolicy
    0.49
    LayoutConstraint
    0.48
    Activations Density 0.095%

    No Known Activations