© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15564
    Prev
    Next
    INDEX
    Explanations

    LaTeX code structure and commands related to document formatting and typesetting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =?";
    -0.51
    chables
    -0.50
     CRUD
    -0.49
    ReusableCell
    -0.46
    IntentFilter
    -0.45
    oblo
    -0.44
    [:]
    -0.44
     RPC
    -0.44
     représent
    -0.44
    ">//
    -0.44
    POSITIVE LOGITS
     LaTeX
    0.87
     latex
    0.84
     Latex
    0.78
    TEX
    0.77
     Te
    0.77
    TeX
    0.76
    Latex
    0.75
     TEX
    0.75
    latex
    0.71
     tex
    0.70
    Activations Density 1.854%

    No Known Activations