© 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. 1794
    Prev
    Next
    INDEX
    Explanations

    specialized notation or symbols typically used in academic or scientific contexts

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

    LaTeX syntax and mathematical expressions in technical or scientific documents.

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

    LaTeX mathematical notation and formatting symbols.

    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
     ages
    -0.40
     sunk
    -0.37
     Cecil
    -0.37
     bury
    -0.36
    ages
    -0.36
    age
    -0.36
    aced
    -0.35
     self
    -0.35
     بلا
    -0.35
     burying
    -0.35
    POSITIVE LOGITS
     avoient
    0.77
    AnimationsModule
    0.75
    webElementXpaths
    0.73
    tagHelperRunner
    0.68
     étoient
    0.65
    httphttps
    0.64
    oa̍t
    0.63
     للاسماء
    0.62
     CreateTagHelper
    0.59
    AndEndTag
    0.58
    Activations Density 0.007%

    No Known Activations