© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2921
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications or authors

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

    citations of physical science research papers or articles with a focus on notation and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Winaray
    -0.96
    ArgsConstructor
    -0.82
    migrationBuilder
    -0.75
    nościo
    -0.72
    yntaxException
    -0.71
    bootstrapcdn
    -0.70
     getItemCount
    -0.68
    లాలు
    -0.66
    declarations
    -0.66
    amerikanische
    -0.62
    POSITIVE LOGITS
     bArr
    0.88
     bVar
    0.81
     getB
    0.78
     BES
    0.78
     Basics
    0.77
     bps
    0.76
     BCS
    0.75
     Bhat
    0.74
     b
    0.73
     BaseModel
    0.73
    Activations Density 1.852%

    No Known Activations