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. 10386
    Prev
    Next
    INDEX
    Explanations

    code related to defining and activating custom element registries in programming

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

    Rust code related to `pub` and `fn`

    np_acts-logits-general · gemini-2.0-flash

    Rust public functions

    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
    enterOuterAlt
    -0.63
    hésite
    -0.63
    DockStyle
    -0.58
    uestamente
    -0.57
    astify
    -0.56
    ölker
    -0.56
    batim
    -0.56
    Rüyada
    -0.55
    onViewCreated
    -0.55
    celess
    -0.55
    POSITIVE LOGITS
    pub
    1.04
    fn
    0.88
     pub
    0.86
     fn
    0.78
    Pub
    0.69
    #[
    0.67
     Pub
    0.67
     PUB
    0.64
     impl
    0.54
     pubs
    0.53
    Activations Density 0.100%

    No Known Activations