© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3913
    Prev
    Next
    INDEX
    Explanations

    Java-related classes and structures used in programming

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

    Code, names, or numbers followed by a parenthesis

    np_acts-logits-general · gemini-2.0-flash

    Pelosi exit / module code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    mybatisplus
    -0.88
     disambiguazione
    -0.86
     gyhoeddwyd
    -0.84
    kháu
    -0.76
    artifactId
    -0.72
    colhead
    -0.71
    MLLoader
    -0.70
    ьаж
    -0.69
    ftagPool
    -0.68
    //});
    -0.68
    POSITIVE LOGITS
    ();
    0.73
    (
    0.64
    (),
    0.58
    ()
    0.56
    ("
    0.55
    ('
    0.55
     {
    0.55
    (){
    0.53
     just
    0.53
    [
    0.53
    Activations Density 0.077%

    No Known Activations