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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13642
    Prev
    Next
    INDEX
    Explanations

    tax-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jereo
    -0.59
    ↵
    -0.59
    DebuggerNonUser
    -0.58
     
    -0.56
     http
    -0.56
     https
    -0.54
    <eos>
    -0.52
    https
    -0.47
    ↵↵
    -0.46
     who
    -0.45
    POSITIVE LOGITS
     Wallflower
    0.73
     CURIAM
    0.73
    Rhestr
    0.69
    WithIOException
    0.66
    fromnode
    0.66
    ergies
    0.63
    ngths
    0.63
     kasarigan
    0.63
    NOPQRST
    0.62
     Daß
    0.62
    Activations Density 0.125%

    No Known Activations