© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8690
    Prev
    Next
    INDEX
    Explanations

    the term "Gro" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     souri
    -0.44
    endIndex
    -0.37
     Zweig
    -0.35
    scm
    -0.35
     abe
    -0.34
     Violin
    -0.33
     CONSUM
    -0.33
    ništvo
    -0.33
     peindre
    -0.33
    nestjs
    -0.32
    POSITIVE LOGITS
     Gro
    1.48
    Gro
    1.48
     gro
    1.38
    gro
    1.32
    GRO
    1.31
     GRO
    1.29
     Groove
    1.11
     gross
    1.09
     Gross
    1.07
     groove
    1.07
    Activations Density 0.601%

    No Known Activations