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. 24-GEMMASCOPE-RES-16K
    6. 14880
    Prev
    Next
    INDEX
    Explanations

    structured data formats or representations

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

    Text fragments including dashes and symbols

    np_acts-logits-general · gemini-2.0-flash

    tissue repair, assess vigorous

    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
     (‘
    -0.94
    ),”
    -0.79
     (“
    -0.75
     («
    -0.72
    =");
    -0.67
     ')
    
    -0.66
     ';
    
    -0.65
    =/
    -0.65
    ’.”
    -0.65
    ='/
    -0.64
    POSITIVE LOGITS
    "
    1.72
    '
    1.28
    “
    0.96
    ''
    0.83
    `
    0.82
    ”
    0.68
    //"
    0.68
    "!
    0.67
    "'
    0.65
    "?
    0.65
    Activations Density 0.074%

    No Known Activations