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. 2695
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming or mathematical concepts

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

    Numbers or letters following special characters: @, Q, B

    np_acts-logits-general · gemini-2.0-flash

    digits and letters following delimiters

    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
    帖最后由
    -0.95
    EndGlobalSection
    -0.81
    исленность
    -0.77
    "],
    
    -0.75
    "])
    
    -0.74
    )";
    
    -0.73
     nahilalakip
    -0.73
    '],
    
    -0.72
    )"),
    -0.71
    ]";
    -0.70
    POSITIVE LOGITS
    2
    0.84
    1
    0.78
    3
    0.76
    4
    0.73
    _
    0.71
    5
    0.63
    6
    0.61
    9
    0.59
    7
    0.56
    8
    0.53
    Activations Density 0.554%

    No Known Activations