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. 23-GEMMASCOPE-RES-131K
    6. 23188
    Prev
    Next
    INDEX
    Explanations

    specific categories or fields in medical and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.65
    VersionUID
    -0.62
     Khusus
    -0.60
    CppMethod
    -0.57
    +#+
    -0.57
    tagHelperRunner
    -0.56
    ValueStyle
    -0.52
    HtmlAttribute
    -0.50
     ModelExpression
    -0.50
    xase
    -0.49
    POSITIVE LOGITS
     Italijanski
    0.50
     Hesper
    0.45
     BIP
    0.45
    CUSSION
    0.44
     sci
    0.43
     STI
    0.43
     Narco
    0.43
     Azer
    0.42
     bif
    0.42
     brom
    0.42
    Activations Density 0.161%

    No Known Activations