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. 31-GEMMASCOPE-RES-16K
    6. 16367
    Prev
    Next
    INDEX
    Explanations

    references to various types of biological assays or experiments involving proteins and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assertAll
    -0.40
     cref
    -0.37
     parcela
    -0.36
    valdi
    -0.34
     Silber
    -0.34
     StringTokenizer
    -0.33
     Cullen
    -0.33
    silen
    -0.33
    看
    -0.32
    localtime
    -0.32
    POSITIVE LOGITS
    +#+#
    0.61
    awtextra
    0.53
     detailsLots
    0.52
     defaultstate
    0.52
     BES
    0.50
    ̈́
    0.49
    ImageContext
    0.48
    twimg
    0.47
    /**
    0.47
     CanadaChoose
    0.47
    Activations Density 0.135%

    No Known Activations