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. 22-GEMMASCOPE-RES-16K
    6. 12891
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with labels and jumps (e.g., "out:")

    np_acts-logits-general · gemini-2.0-flash

    out:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.78
    IonicModule
    -0.77
    Xna
    -0.75
    Kaieteur
    -0.71
    AllAfrica
    -0.71
    AsUp
    -0.71
     atof
    -0.71
    providedIn
    -0.70
    ientôt
    -0.70
    ⋙
    -0.69
    POSITIVE LOGITS
    out
    0.59
    next
    0.57
    tr
    0.52
    again
    0.51
     out
    0.50
    ic
    0.49
    Out
    0.48
    _
    0.48
    我了
    0.48
    #
    0.48
    Activations Density 0.195%

    No Known Activations