© 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. 36-GEMMASCOPE-RES-16K
    11. 16027
    Prev
    Next
    INDEX
    Explanations

    references to the word "gre" and its variations, indicating a focus on topics related to "green" or similar terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEVELOP
    -0.39
    BufferException
    -0.39
    eqnarray
    -0.38
    ClientSize
    -0.38
    Glu
    -0.37
     nt
    -0.37
     Glu
    -0.36
     Automate
    -0.36
    desliz
    -0.35
    DRS
    -0.35
    POSITIVE LOGITS
     Gre
    0.77
    Gre
    0.77
     gre
    0.73
     autorytatywna
    0.72
    OGND
    0.63
    gre
    0.61
     Гре
    0.60
     GRE
    0.59
     griech
    0.57
    GRE
    0.56
    Activations Density 0.188%

    No Known Activations