© 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. 22-GEMMASCOPE-RES-16K
    11. 5767
    Prev
    Next
    INDEX
    Explanations

    historical figures and their connections to governance and political roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Насе
    -0.54
     betweenstory
    -0.52
     attractiveness
    -0.51
    汰
    -0.51
     prioritized
    -0.50
    convite
    -0.50
     universality
    -0.49
    RenderAtEndOf
    -0.49
    volve
    -0.49
    rizona
    -0.49
    POSITIVE LOGITS
    webElementXpaths
    0.36
     metra
    0.36
    whose
    0.35
    later
    0.35
     who
    0.34
    BeginContext
    0.33
    known
    0.32
     terkenal
    0.31
     whose
    0.31
     famous
    0.31
    Activations Density 0.428%

    No Known Activations