© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6766
    Prev
    Next
    INDEX
    Explanations

    expressions and references related to warmth and comfort

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

    Following "warm"

    np_acts-logits-general · gemini-2.0-flash

    warm + adjective/noun/action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.81
    EDEFAULT
    -0.65
     Administrativna
    -0.65
     onOptions
    -0.62
    Rohy
    -0.61
     Normdatei
    -0.60
     Zwer
    -0.58
     Tsche
    -0.58
     AssemblyCulture
    -0.58
    yntaxException
    -0.58
    POSITIVE LOGITS
     warms
    0.97
     cálido
    0.89
    WARM
    0.87
    warm
    0.87
     warm
    0.80
     Warm
    0.80
     WARM
    0.79
     snippetHide
    0.77
     warmth
    0.77
    Warm
    0.76
    Activations Density 0.054%

    No Known Activations