© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12542
    Prev
    Next
    INDEX
    Explanations

    elements associated with legal responsibilities and compliance in various contexts

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

    preceding lists or series

    np_acts-logits-general · gemini-2.0-flash

    time, place, during, or conditions

    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
     '/';
    -0.80
     "/";
    -0.71
    :
    -0.66
     '-';
    -0.61
    SourceChecksum
    -0.60
    :(
    -0.60
     mengingat
    -0.60
     visst
    -0.59
     porque
    -0.58
     eftersom
    -0.57
    POSITIVE LOGITS
     etc
    1.08
    migrationBuilder
    0.84
    etc
    0.80
     ETC
    0.75
    Rhestr
    0.74
     Etc
    0.73
    providedIn
    0.71
     usw
    0.70
     ect
    0.67
    RUnlock
    0.67
    Activations Density 0.386%

    No Known Activations