© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6182
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements related to layout and structure

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

    HTML and CSS class attributes in web markup.

    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
    httphttps
    -0.42
     كومونز
    -0.41
    EndInit
    -0.41
    unk
    -0.37
    xac
    -0.36
    勿論
    -0.36
    into
    -0.36
    fär
    -0.35
    indest
    -0.35
    llo
    -0.33
    POSITIVE LOGITS
    SharedCtor
    0.63
     kaarangay
    0.62
    StoryboardSegue
    0.57
    㗎
    0.50
    exitRule
    0.50
    脚注の使い方
    0.50
     насељу
    0.50
     doInBackground
    0.49
     ujednoznacz
    0.48
    addContainerGap
    0.47
    Activations Density 0.065%

    No Known Activations