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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7904
    Prev
    Next
    INDEX
    Explanations

    terms related to software tools and conversion processes

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

    Follows a verb or preposition

    np_acts-logits-general · gemini-2.0-flash

    mentions of specific software

    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
     himſelf
    -0.66
     chi̍t
    -0.59
     houſe
    -0.58
     OpenGL
    -0.57
     reaſon
    -0.57
     juſ
    -0.57
     Jefus
    -0.57
     pleaſure
    -0.56
    AxisAlignment
    -0.56
     Anfitrión
    -0.56
    POSITIVE LOGITS
     programmi
    0.59
     Total
    0.56
    Total
    0.56
     programas
    0.56
    AddTagHelper
    0.53
     программу
    0.52
     programmet
    0.52
     kostenlose
    0.48
     initComponents
    0.48
     kostenlosen
    0.48
    Activations Density 0.428%

    No Known Activations