© 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. 9-GEMMASCOPE-RES-16K
    11. 9549
    Prev
    Next
    INDEX
    Explanations

    terms associated with greatness or significant achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.59
    IntoConstraints
    -0.57
    MLLoader
    -0.55
     برانيه
    -0.54
     dodgy
    -0.53
    AndEndTag
    -0.53
    ագրություններ
    -0.52
     transfieras
    -0.52
     cheeky
    -0.52
    munition
    -0.51
    POSITIVE LOGITS
     great
    1.65
    great
    1.55
     Great
    1.50
    Great
    1.47
     GREAT
    1.41
    GREAT
    1.36
     greatest
    1.06
    TheGreat
    1.00
    greatest
    0.96
     greater
    0.92
    Activations Density 0.303%

    No Known Activations