Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6088
    Prev
    Next
    INDEX
    Explanations

    instances of the word "warm" and related terms that convey warmth or comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemCount
    -0.82
     تانيه
    -0.80
     Schmitt
    -0.77
     pellic
    -0.73
     effray
    -0.72
    例句
    -0.71
    elts
    -0.69
     recruiter
    -0.69
    astéroïdes
    -0.68
    bolista
    -0.68
    POSITIVE LOGITS
     Warm
    1.28
    WARM
    1.25
     WARM
    1.25
    warm
    1.24
     warmth
    1.24
     warm
    1.21
    Warm
    1.19
     warms
    1.19
     warmer
    1.13
     warmest
    1.08
    Activations Density 0.043%

    No Known Activations