© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15806
    Prev
    Next
    INDEX
    Explanations

    quantifiable outcomes related to legal or medical evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.45
     citoy
    -0.45
    AndEndTag
    -0.42
     sanitaire
    -0.42
     compacto
    -0.40
    ThroughAttribute
    -0.40
    satisfied
    -0.40
     Warga
    -0.40
    uvre
    -0.40
    
    -0.39
    POSITIVE LOGITS
    createClass
    0.40
    ressee
    0.40
    WebpackPlugin
    0.40
    NewReader
    0.39
    TagHelper
    0.37
    OfClass
    0.36
     cro
    0.36
    rovnik
    0.36
    ✭✭
    0.36
    yarnpkg
    0.36
    Activations Density 1.061%

    No Known Activations