© 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. 40-GEMMASCOPE-RES-16K
    6. 5579
    Prev
    Next
    INDEX
    Explanations

    high numeric values associated with API request functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.43
    makeText
    -0.40
     HttpNotFound
    -0.38
    Fatalf
    -0.38
     joaat
    -0.36
    iems
    -0.35
    awtextra
    -0.35
     חיצוניים
    -0.35
    gemeen
    -0.35
     ویکی‌پدیای
    -0.35
    POSITIVE LOGITS
        
    1.23
     tartalomajánló
    0.48
     '\\;'
    0.42
    Ligações
    0.41
    rungsseite
    0.40
    endwhile
    0.39
    tênis
    0.39
    issory
    0.38
    regon
    0.37
    󠁴
    0.37
    Activations Density 0.351%

    No Known Activations