© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3326
    Prev
    Next
    INDEX
    Explanations

    expressions and commands related to LaTeX document preparation

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

    LaTeX code and markup syntax.

    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
    +#+
    -0.69
     mergeFrom
    -0.68
    tonode
    -0.64
    ConstraintMaker
    -0.64
    InitVars
    -0.61
    MockBean
    -0.60
    verifyException
    -0.60
    IsContent
    -0.59
    ]=>
    -0.59
    ftagPool
    -0.59
    POSITIVE LOGITS
    ↵↵
    0.41
     Internasional
    0.39
    Consequences
    0.36
     illustrationer
    0.36
     mariée
    0.36
     Throughout
    0.34
    本文
    0.34
     Demokratie
    0.34
    ↵↵↵
    0.33
     aérienne
    0.33
    Activations Density 0.139%

    No Known Activations