© 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. 20-GEMMASCOPE-RES-16K
    6. 1878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the role and importance of various factors or elements within a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific phrases discussing "the role of" something in various contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    řel
    -0.47
     McRae
    -0.41
     sitten
    -0.41
     싶
    -0.40
     itſelf
    -0.39
     administracy
    -0.38
    catchError
    -0.38
     ciò
    -0.38
     houſe
    -0.37
    andale
    -0.37
    POSITIVE LOGITS
    ChildIndex
    0.65
     Role
    0.59
     Importance
    0.57
     role
    0.53
     importance
    0.52
    webElementXpaths
    0.52
    endregion
    0.51
    Role
    0.51
    Importance
    0.51
     Contribution
    0.50
    Activations Density 0.308%

    No Known Activations