© 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. 31-GEMMASCOPE-RES-16K
    11. 102
    Prev
    Next
    INDEX
    Explanations

    specific locations, particularly geographic or venue names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geographic location names and addresses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    calientes
    -0.50
     Minangkabau
    -0.37
    parfum
    -0.35
     dedans
    -0.35
    ลำ
    -0.34
    jMenuItem
    -0.34
    fahan
    -0.34
    atorul
    -0.34
     HasFactory
    -0.34
     Telangana
    -0.33
    POSITIVE LOGITS
     beach
    1.49
     seaside
    1.32
    Beach
    1.29
     beachfront
    1.27
     Beach
    1.27
     coastal
    1.26
    beach
    1.23
     seashore
    1.20
     Coastal
    1.15
     Seaside
    1.15
    Activations Density 0.394%

    No Known Activations