© 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. 4-GEMMASCOPE-RES-16K
    11. 15746
    Prev
    Next
    INDEX
    Explanations

    mentions of "range" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blessé
    -0.83
     Mooney
    -0.77
     Witkin
    -0.73
     Nutt
    -0.72
     journalistes
    -0.72
     Mistakes
    -0.71
     bookId
    -0.70
     Borel
    -0.70
     Gehir
    -0.70
     pitié
    -0.69
    POSITIVE LOGITS
     range
    2.82
     ranges
    2.63
     Range
    2.58
    range
    2.50
     RANGE
    2.43
    Range
    2.40
    ranges
    2.22
    RANGE
    2.22
     Ranges
    2.17
    Ranges
    2.04
    Activations Density 0.073%

    No Known Activations