© 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. 15119
    Prev
    Next
    INDEX
    Explanations

    CSS style definitions and color specifications in code

    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
    CreateModel
    -0.62
     gyhoeddwyd
    -0.60
    __(/*!
    -0.48
    velocityY
    -0.48
    RenderAtEndOf
    -0.48
    tocin
    -0.46
     مرئيه
    -0.44
     gian
    -0.44
     microm
    -0.44
    actylus
    -0.44
    POSITIVE LOGITS
     background
    1.06
     Background
    0.98
    background
    0.95
     BACKGROUND
    0.95
    Background
    0.94
    BACKGROUND
    0.92
     backgrounds
    0.90
     border
    0.86
     Hintergrund
    0.84
     highlight
    0.83
    Activations Density 0.385%

    No Known Activations