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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8538
    Prev
    Next
    INDEX
    Explanations

    references to temperature, specifically cold-related terms and phrases

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

    low temperature

    np_acts-logits-general · gemini-2.0-flash

    temperature and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.54
     CURIAM
    -0.47
    llium
    -0.47
    LabelTagHelper
    -0.46
     Effort
    -0.46
    shund
    -0.46
    endpush
    -0.45
     Administrativna
    -0.45
     useParams
    -0.44
    pulseira
    -0.44
    POSITIVE LOGITS
     Cold
    1.01
    Cold
    1.00
     cold
    0.96
    cold
    0.90
     COLD
    0.85
     cool
    0.84
     Cool
    0.84
    Cool
    0.84
    COLD
    0.81
     COOL
    0.81
    Activations Density 0.103%

    No Known Activations