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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 128
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and data structure definitions related to network protocols and packet handling

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

    code and programming syntax, particularly XML and macro definitions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Efq
    -0.55
     getLogin
    -0.53
     doubtnut
    -0.50
    setAccessible
    -0.49
    AddHtmlAttribute
    -0.48
    Fordítás
    -0.48
     getCode
    -0.48
     proyección
    -0.48
     você
    -0.48
    zystać
    -0.47
    POSITIVE LOGITS
     M
    1.02
     m
    0.85
    M
    0.82
     MH
    0.77
    m
    0.72
     М
    0.71
     MC
    0.69
    ConstraintMaker
    0.69
     MB
    0.68
     MA
    0.68
    Activations Density 2.192%

    No Known Activations