© 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. 31-GEMMASCOPE-RES-16K
    11. 12261
    Prev
    Next
    INDEX
    Explanations

    specific phrases and words related to greetings and farewells

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

    Cyrillic and non-Latin script text strings in source code and localization files.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.44
     rehe
    -0.40
    NewLabel
    -0.38
     sear
    -0.37
     Италијани
    -0.36
    enderror
    -0.35
    scribers
    -0.33
    apatalk
    -0.33
    endphp
    -0.33
    testing
    -0.33
    POSITIVE LOGITS
    WebControls
    0.50
    derive
    0.49
     defaultstate
    0.49
    脚注の使い方
    0.49
     khi
    0.49
    sizeCache
    0.46
    ValueStyle
    0.44
    numerusform
    0.44
    Contributed
    0.43
    HtmlAttribute
    0.42
    Activations Density 0.068%

    No Known Activations