© 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. 13655
    Prev
    Next
    INDEX
    Explanations

    programming control structures and variable declarations

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

    loop variable increments in for loops.

    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
     незавершена
    -0.91
    Хьажоргаш
    -0.88
     Италијани
    -0.85
     Мексичка
    -0.82
    parsedMessage
    -0.81
     OMITBAD
    -0.79
     snippetHide
    -0.79
    uxxxx
    -0.77
    aarrggbb
    -0.76
    ImageContext
    -0.73
    POSITIVE LOGITS
    ++)
    0.37
     bertambah
    0.34
     Funktions
    0.32
    ++
    0.31
     semakin
    0.31
     +=
    0.30
     creciente
    0.30
     étranger
    0.30
     step
    0.29
    Step
    0.29
    Activations Density 0.032%

    No Known Activations