© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104626
    Prev
    Next
    INDEX
    Explanations

    terms related to 'chill' or coolness, both in a literal and metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.57
     Administrativna
    -0.56
     GME
    -0.56
     Abram
    -0.53
     Manu
    -0.53
     PDS
    -0.53
     representation
    -0.53
    naeus
    -0.52
     Ause
    -0.52
    carpus
    -0.51
    POSITIVE LOGITS
     Chill
    1.10
    Chill
    1.07
    chill
    0.94
     chill
    0.79
     chilli
    0.69
     Chilli
    0.68
     Chili
    0.67
    Chili
    0.66
    chili
    0.65
    Chi
    0.60
    Activations Density 0.003%

    No Known Activations