© 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. 41-GEMMASCOPE-RES-16K
    11. 7006
    Prev
    Next
    INDEX
    Explanations

    references to class or type identifiers in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writerow
    -0.44
     utafitiHapana
    -0.42
    phosa
    -0.41
     Sor
    -0.40
    nofollow
    -0.39
    conditionally
    -0.39
    ScopeManager
    -0.38
    immune
    -0.38
     Holl
    -0.38
     Cau
    -0.38
    POSITIVE LOGITS
    Jeografia
    0.41
    MLLoader
    0.39
    dk
    0.38
    :\\
    0.36
    sspiel
    0.34
     Audiodateien
    0.34
     Савезне
    0.34
    apiClient
    0.33
    papi
    0.33
    ss
    0.33
    Activations Density 0.823%

    No Known Activations