© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12971
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and evaluations within equations and expressions

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

    mathematical operations and symbols in equations, especially in problem-solving contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.73
     وتسجيلات
    -0.68
    principalColumn
    -0.66
    Hentet
    -0.65
    pherals
    -0.60
    AndEndTag
    -0.59
    ########.
    -0.59
    IDATE
    -0.58
     стоковое
    -0.58
    isContained
    -0.58
    POSITIVE LOGITS
    providedIn
    0.44
     âme
    0.31
    jsxFileName
    0.29
     lendemain
    0.28
    LookAnd
    0.27
     témoignage
    0.27
     viñ
    0.27
     sés
    0.26
     Meksiku
    0.26
     hvid
    0.26
    Activations Density 2.654%

    No Known Activations