© 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. 8401
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific methodology and research practices

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

    words that describe technical functionality, particularly verbs like "installed," "connected," "designed," "reconstructed," and "optimized" that relate to engineering and technical systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    adjectives describing practical utility or beneficial outcomes (useful, important, beneficial).

    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
     mergeFrom
    -0.54
    Personensuche
    -0.46
    INSEE
    -0.44
    Spoljašnje
    -0.41
     beginnetje
    -0.40
    prnewswire
    -0.40
     aDecoder
    -0.39
    -------
    -0.39
    MenuInflater
    -0.39
    ContentAsync
    -0.38
    POSITIVE LOGITS
     appunto
    0.54
    MigrationBuilder
    0.54
     perhaps
    0.50
     noDo
    0.49
    AddHtmlAttribute
    0.45
     quizá
    0.44
     gyhoeddwyd
    0.43
    pecially
    0.43
    perhaps
    0.42
    uding
    0.42
    Activations Density 0.864%

    No Known Activations