© 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. 9258
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets related to currencies and regions

    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
    ViewImports
    -0.50
     Harg
    -0.32
     Verhält
    -0.31
     AssemblyVersion
    -0.30
     AssemblyCompany
    -0.30
     seleccion
    -0.30
     вида
    -0.29
    combined
    -0.29
     close
    -0.29
    tomorrow
    -0.29
    POSITIVE LOGITS
     almohada
    0.56
    Erreferentziak
    0.53
    verwijspagina
    0.53
    majánló
    0.52
     témoig
    0.52
    ésultats
    0.52
     unterkunft
    0.52
    ranean
    0.51
    Packard
    0.50
     Monfieur
    0.50
    Activations Density 0.345%

    No Known Activations