© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 6401
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking or baking processes

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

    cooling and cooled states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    IntoConstraints
    -0.71
    complexContent
    -0.54
     kaarangay
    -0.54
     propOrder
    -0.52
     صوتيه
    -0.51
    utives
    -0.50
    InjectMocks
    -0.49
    GraphicsUnit
    -0.48
    GenerationType
    -0.48
    EndGlobalSection
    -0.48
    POSITIVE LOGITS
     cooling
    1.46
     cools
    1.36
     cooled
    1.34
     Cooling
    1.30
    cooling
    1.27
    Cooling
    1.26
     cool
    1.18
     Cool
    1.12
    cooled
    1.07
     coolness
    1.07
    Activations Density 0.028%

    No Known Activations