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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 6080
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and their contextual significance

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

    technical or procedural language, especially related to specific research aims, legal documents, or scientific methodologies.

    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
     AssemblyCulture
    -0.99
     kasarigan
    -0.98
     ModelExpression
    -0.96
     autorytatywna
    -0.87
    RenderAtEndOf
    -0.86
     يتيمه
    -0.82
     mergeFrom
    -0.81
     CreateTagHelper
    -0.80
     समीक्षाओं
    -0.79
     Normdatei
    -0.79
    POSITIVE LOGITS
    <eos>
    0.51
     aş
    0.40
    fast
    0.40
    Open
    0.39
    Fast
    0.39
    ISE
    0.38
    cle
    0.36
    回
    0.35
    OR
    0.35
    ZT
    0.35
    Activations Density 0.069%

    No Known Activations