© 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. 37-GEMMASCOPE-RES-16K
    6. 712
    Prev
    Next
    INDEX
    Explanations

    references to recent scientific research and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enriched
    -0.34
     entera
    -0.33
     varm
    -0.31
    🧮
    -0.31
     au
    -0.31
     eser
    -0.30
     bestätigen
    -0.30
     signal
    -0.30
     panel
    -0.30
     bestehen
    -0.29
    POSITIVE LOGITS
    SourceChecksum
    0.62
     nakalista
    0.60
    évaluateur
    0.59
    rungsseite
    0.57
     Langmuir
    0.56
    ValueStyle
    0.56
    afficheront
    0.56
     FetchType
    0.55
     &___
    0.54
    Carriera
    0.53
    Activations Density 0.537%

    No Known Activations