© 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. 7-GEMMASCOPE-RES-16K
    11. 15869
    Prev
    Next
    INDEX
    Explanations

    specific location names, particularly road and street names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.78
    RenderAtEndOf
    -0.75
    Hauptartikel
    -0.62
    Espèce
    -0.60
    Referencies
    -0.55
    posedge
    -0.54
     فريبيس
    -0.53
    addContainerGap
    -0.51
    oa̍t
    -0.50
     المعيارى
    -0.49
    POSITIVE LOGITS
    writerow
    0.35
     Blvd
    0.34
    writeTo
    0.34
    printf
    0.33
     Rd
    0.33
    ナス
    0.32
     cauliflower
    0.32
     国道
    0.31
    setVisibility
    0.31
    esgue
    0.31
    Activations Density 0.355%

    No Known Activations