© 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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 64
    Prev
    Next
    INDEX
    Explanations

    terms related to eating habits and dietary choices

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

    actions and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pourtant
    -0.34
    kammer
    -0.33
     atividade
    -0.30
     deber
    -0.29
     крае
    -0.29
     this
    -0.29
    entretien
    -0.29
    cat
    -0.29
     par
    -0.28
     éton
    -0.28
    POSITIVE LOGITS
     InputDecoration
    0.66
    SequentialGroup
    0.65
    migrationBuilder
    0.65
     CallOverrides
    0.63
     leſs
    0.61
    OGND
    0.59
    featureID
    0.58
     DbType
    0.58
    ⟬
    0.57
    AnchorStyles
    0.57
    Activations Density 0.032%

    No Known Activations