© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5676
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical expressions involving exclusions and conditions

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

    mathematical and computational terminology and symbols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    AccessorTable
    -0.37
    Portail
    -0.32
     amarillas
    -0.31
    ispiel
    -0.30
     hendes
    -0.29
    สบ
    -0.29
     Anlass
    -0.29
     allá
    -0.29
     Gestão
    -0.28
     thôi
    -0.28
    POSITIVE LOGITS
    MigrationBuilder
    0.68
     CreateTagHelper
    0.59
    setVerticalGroup
    0.56
     initComponents
    0.56
    VersionUID
    0.55
     exclusions
    0.54
    complexContent
    0.54
    :✨
    0.54
    RTLR
    0.53
     Exclude
    0.52
    Activations Density 0.342%

    No Known Activations