© 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. 37-GEMMASCOPE-RES-16K
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    phrases related to data storage and computing resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postsleuth
    -0.39
     mold
    -0.31
     mat
    -0.30
    ตุ
    -0.29
     boom
    -0.29
     Sergio
    -0.29
     binh
    -0.29
    กุ
    -0.29
    mlx
    -0.29
    lem
    -0.28
    POSITIVE LOGITS
     Meg
    1.16
     meg
    1.16
     gig
    1.13
     Gig
    1.13
    Gig
    1.13
    Meg
    1.07
     MB
    1.05
     GIG
    1.05
    meg
    1.05
    gig
    1.02
    Activations Density 0.594%

    No Known Activations