© 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. 11-GEMMASCOPE-RES-16K
    6. 4941
    Prev
    Next
    INDEX
    Explanations

    causal relationships and outcomes in events or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.60
     betweenstory
    -0.59
     tartalomajánló
    -0.54
     itſelf
    -0.54
     resultCode
    -0.54
     TType
    -0.54
    StoryboardSegue
    -0.52
    ſelves
    -0.51
    səhifə
    -0.51
    RenderAtEndOf
    -0.50
    POSITIVE LOGITS
     by
    0.40
     disambiguazione
    0.36
     durch
    0.36
     disebabkan
    0.35
    autoreleasepool
    0.34
    ustre
    0.33
    damente
    0.33
    urah
    0.33
     adanya
    0.32
     yolu
    0.32
    Activations Density 1.484%

    No Known Activations