© 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. 24-GEMMASCOPE-RES-16K
    11. 2447
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical data and statistics

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

    Tokens followed by "1" or mentioning monetary values

    np_acts-logits-general · gemini-2.0-flash

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.63
    ۰
    -0.57
    φων
    -0.56
    WAP
    -0.55
     ২০
    -0.54
    ٠
    -0.54
     bille
    -0.53
    strukt
    -0.53
    ۰۱
    -0.52
    maila
    -0.52
    POSITIVE LOGITS
    ContentAsync
    0.59
     rospy
    0.59
     endwhile
    0.52
    SupportActionBar
    0.50
    ayuno
    0.49
    clyde
    0.49
    XMLSchema
    0.49
     Ebola
    0.47
     Zika
    0.46
    ngdoc
    0.46
    Activations Density 0.088%

    No Known Activations