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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 14373
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to graph theory and relations

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

    Mathematical or logical symbols

    np_acts-logits-general · gemini-2.0-flash

    arrows and implications

    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
    %");
    -0.57
    Personendaten
    -0.56
    ]--;
    -0.55
    ".
    
    -0.53
    }:${
    -0.53
    "},
    
    -0.53
    %";
    -0.52
    .";
    
    -0.51
    amaño
    -0.50
     Spot
    -0.50
    POSITIVE LOGITS
     →
    0.88
    ->
    0.83
     ->
    0.82
     =>
    0.74
    →
    0.72
    AddTagHelper
    0.71
     -->
    0.70
     >>
    0.69
     arrows
    0.69
     arrow
    0.67
    Activations Density 0.598%

    No Known Activations