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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1835
    Prev
    Next
    INDEX
    Explanations

    programming and scripting commands related to variables and data handling

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

    Excel VBA code snippets

    np_acts-logits-general · gemini-2.0-flash

    variable assignments and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /');
    -0.92
    )");
    
    -0.87
     $_"
    -0.84
    ]");
    -0.84
    )');
    -0.82
     }}$}
    -0.81
    */;
    -0.80
    /");
    -0.79
     pinulongan
    -0.79
    出版年
    -0.78
    POSITIVE LOGITS
    :=
    0.45
     :=
    0.42
     vb
    0.42
    randi
    0.40
    GOS
    0.40
     intérprete
    0.39
    されると
    0.39
     blanks
    0.39
    reactstrap
    0.38
     Nothing
    0.38
    Activations Density 0.617%

    No Known Activations