© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9560
    Prev
    Next
    INDEX
    Explanations

    specific references to locations or geographical features

    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
    EndContext
    -0.51
     AssemblyCulture
    -0.49
     typelib
    -0.47
     CURLOPT
    -0.43
    MigrationBuilder
    -0.40
    angulaire
    -0.38
     AssemblyVersion
    -0.36
    PyExc
    -0.35
    GEBURTSDATUM
    -0.35
    ьаж
    -0.35
    POSITIVE LOGITS
     Outer
    0.64
     Intra
    0.60
    Outer
    0.59
     Hatter
    0.57
     Barrier
    0.54
     Inlet
    0.54
    Intra
    0.54
     barrier
    0.52
     pleaſure
    0.51
     Folly
    0.49
    Activations Density 0.314%

    No Known Activations