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. 21-GEMMASCOPE-RES-16K
    6. 717
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with scientific classification and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Farley
    -0.51
    ,
    -0.47
     fusca
    -0.45
     Freitas
    -0.44
     Oliveira
    -0.44
     Lippen
    -0.44
    e
    -0.44
     Ketten
    -0.44
     Feldman
    -0.42
    hip
    -0.42
    POSITIVE LOGITS
    ьаж
    0.67
    errHandler
    0.66
     صوتيه
    0.65
     CURIAM
    0.63
    setTransform
    0.61
    strator
    0.60
    ſelves
    0.60
    tonode
    0.60
    endgroup
    0.60
    تقاوى
    0.59
    Activations Density 1.770%

    No Known Activations