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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1020
    Prev
    Next
    INDEX
    Explanations

    parts of a mechanical or operational structure

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

    describes state or relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.72
    aarrggbb
    -0.52
    ]<<"
    -0.50
     plufieurs
    -0.48
    jooq
    -0.48
     ſind
    -0.47
     auroit
    -0.46
    SqlClient
    -0.46
     $_"
    -0.46
     occaf
    -0.45
    POSITIVE LOGITS
     was
    0.77
     had
    0.69
     tended
    0.69
     lacked
    0.67
     depended
    0.66
     differed
    0.63
     showed
    0.62
     belonged
    0.62
     resembled
    0.62
     gave
    0.60
    Activations Density 0.121%

    No Known Activations