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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15586
    Prev
    Next
    INDEX
    Explanations

    names or identifiers related to various subjects

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

    Tokens preceding "ay," "ne," or "ro"

    np_acts-logits-general · gemini-2.0-flash

    Dun derivatives

    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
     least
    -0.54
    Попис
    -0.53
     else
    -0.52
    terase
    -0.50
    dear
    -0.48
    taires
    -0.48
    existsSync
    -0.47
    else
    -0.47
    zyk
    -0.46
    asca
    -0.46
    POSITIVE LOGITS
    synd
    0.67
    shaft
    0.64
    stein
    0.63
    sen
    0.63
    PerformLayout
    0.62
    shine
    0.59
    sha
    0.57
    save
    0.57
    sky
    0.57
    ste
    0.56
    Activations Density 0.121%

    No Known Activations