© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9803
    Prev
    Next
    INDEX
    Explanations

    specific references to different approaches, phases, or formats in a structured manner

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

    "first" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    first (or second) in a list/sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.57
     مشين
    -0.55
     صوتيه
    -0.47
    PerformLayout
    -0.46
     OFDb
    -0.39
    Rog
    -0.38
    Đ
    -0.37
    Something
    -0.37
    ┐
    -0.36
     thereafter
    -0.36
    POSITIVE LOGITS
     portion
    0.52
     version
    0.47
    помним
    0.46
     isNameExpr
    0.46
     component
    0.45
     layer
    0.44
    principalColumn
    0.43
     side
    0.42
     Variante
    0.42
     venue
    0.41
    Activations Density 0.848%

    No Known Activations