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. 20-GEMMASCOPE-RES-65K
    6. 984
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values

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

    numerical values associated with coding or computing contexts

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

    code and citations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ----</
    -0.50
    ดับ
    -0.49
    DMETHOD
    -0.49
    rhosis
    -0.48
    rawl
    -0.47
     تانيه
    -0.47
     wors
    -0.46
     плюс
    -0.45
    DeepCopy
    -0.45
    vial
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.86
     <<<<<<<<<<<<<<
    0.85
    \}\\
    0.74
    ReusableCell
    0.70
    SpringBootTest
    0.69
    tvguidetime
    0.68
    /');
    0.65
    getMenuInflater
    0.65
    glMatrixMode
    0.61
    ())));
    0.60
    Activations Density 0.021%

    No Known Activations