© 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. 31-GEMMASCOPE-RES-16K
    6. 1148
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical recommendations and treatment plans

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

    phrases related to origin, location, or place.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    the phrase "of" followed by a noun referring to a location or origin.

    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
     thermique
    -0.44
     ***!
    -0.41
     termica
    -0.40
    migrationBuilder
    -0.40
     ModelExpression
    -0.38
     tournant
    -0.37
    Personensuche
    -0.37
     térmica
    -0.36
     acrylique
    -0.36
     policiales
    -0.36
    POSITIVE LOGITS
     disambiguazione
    0.58
     ofre
    0.52
     operation
    0.52
     autorytatywna
    0.50
    オブ
    0.50
     saites
    0.47
    Autoritní
    0.46
     Aufen
    0.46
    การ
    0.46
     Wikiseite
    0.46
    Activations Density 0.725%

    No Known Activations