© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11355
    Prev
    Next
    INDEX
    Explanations

    references to authorship, revisions, and discussion of manuscript feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.57
     nakalista
    -0.54
    UrlResolution
    -0.51
    velocityY
    -0.49
    iibo
    -0.49
    脚注の使い方
    -0.48
    RTLI
    -0.47
     AssemblyCulture
    -0.47
    úgó
    -0.47
    andExpect
    -0.44
    POSITIVE LOGITS
     version
    1.52
     Version
    1.31
    version
    1.25
     versions
    1.23
     versión
    1.17
    Version
    1.16
    版本
    1.16
     revised
    1.14
     VERSION
    1.13
     versão
    1.09
    Activations Density 0.526%

    No Known Activations