© 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. 9-GEMMASCOPE-RES-16K
    11. 2568
    Prev
    Next
    INDEX
    Explanations

    instances of the word "various" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -0.68
    ck
    -0.58
    k
    -0.56
    й
    -0.56
    CT
    -0.55
     économies
    -0.55
    lid
    -0.54
    ख
    -0.54
    lyn
    -0.53
    let
    -0.53
    POSITIVE LOGITS
     various
    1.32
    various
    1.32
    Various
    1.27
     Various
    1.26
     kinds
    1.25
     assorted
    1.22
     nahilalakip
    1.22
     sundry
    1.19
     VARIOUS
    1.14
    httphttps
    1.14
    Activations Density 0.073%

    No Known Activations