© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 5666
    Prev
    Next
    INDEX
    Explanations

    numerical data and references in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.82
    bootstrapcdn
    -0.79
    UnknownFields
    -0.75
    ReusableCell
    -0.75
    !*\
    -0.73
    webElement
    -0.69
    ⋙
    -0.68
    leau
    -0.68
    — 
    -0.68
    исленность
    -0.67
    POSITIVE LOGITS
     CURIAM
    0.52
    blaze
    0.48
    enderror
    0.47
    esModule
    0.46
     Referential
    0.46
    antaine
    0.46
     Breakout
    0.44
     Blaze
    0.43
    break
    0.43
     Räume
    0.42
    Activations Density 0.505%

    No Known Activations