© 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. 25-GEMMASCOPE-RES-16K
    11. 8876
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific phrases or condensed terms, particularly "Th" or variations of "th."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nonatomic
    -0.65
    .*")]
    -0.65
     "..\..\
    -0.62
     nonatomic
    -0.61
    $_['
    -0.57
     lenker
    -0.57
     protoimpl
    -0.55
     BoxFit
    -0.54
    autoIncrement
    -0.53
    InitVars
    -0.52
    POSITIVE LOGITS
    unders
    0.59
    rifty
    0.59
    warts
    0.51
    undering
    0.50
    rashed
    0.49
    findpost
    0.49
    erape
    0.48
     Transfermarkt
    0.48
    warted
    0.48
    enterOuterAlt
    0.48
    Activations Density 0.221%

    No Known Activations