© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16000
    Prev
    Next
    INDEX
    Explanations

    references to "cro" and its variations, particularly relating to animals and geographical locations associated with "Crocodile."

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

    words containing the substring "cro" (as in "croc," "crone," "crotch," "cron," "chromosome").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cellspacing
    -0.40
     FormsModule
    -0.39
     Effectiveness
    -0.36
     Antic
    -0.35
    ArgumentParser
    -0.35
    Engines
    -0.35
     Fes
    -0.34
    GroupLayout
    -0.34
     Frederic
    -0.33
    Pound
    -0.33
    POSITIVE LOGITS
     Cro
    0.66
    Cro
    0.63
     CRO
    0.60
     cro
    0.59
     kro
    0.58
     Kro
    0.57
     Croatia
    0.56
    TypedDataSet
    0.56
     CHRON
    0.55
    Croatia
    0.54
    Activations Density 0.132%

    No Known Activations