© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13695
    Prev
    Next
    INDEX
    Explanations

    references to cold temperatures or cold-related conditions

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

    The token "Cold" and related contexts

    np_acts-logits-general · gemini-2.0-flash

    Cold War and cold physical states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.67
     صوتيه
    -0.67
    GEBURTSDATUM
    -0.66
    Portail
    -0.65
    ppuden
    -0.64
     normaux
    -0.63
     étoient
    -0.63
     MainAxisSize
    -0.62
    yntaxException
    -0.61
    AndEndTag
    -0.60
    POSITIVE LOGITS
     cold
    1.09
     Cold
    1.08
    Cold
    1.04
     COLD
    1.01
    COLD
    0.97
    cold
    0.95
     coldest
    0.78
    冷
    0.74
     chilly
    0.73
     weather
    0.71
    Activations Density 0.043%

    No Known Activations