© 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. 15847
    Prev
    Next
    INDEX
    Explanations

    closing brackets and parentheses in code snippets

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

    closing braces and curly brackets that end code blocks or function definitions.

    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
     transfieras
    -0.57
    posedge
    -0.56
    tagHelperRunner
    -0.55
     Infórmanos
    -0.52
     مشين
    -0.51
    sidemargin
    -0.49
    queryInterface
    -0.49
    ngdoc
    -0.48
    DoubleQuotes
    -0.48
    SpringRunner
    -0.48
    POSITIVE LOGITS
     exemplu
    0.46
     Zahlung
    0.45
     puteți
    0.41
    føring
    0.41
     ogen
    0.41
     obrazu
    0.40
    amling
    0.39
     viață
    0.38
    maßen
    0.38
    czego
    0.38
    Activations Density 0.134%

    No Known Activations