© 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. 31-GEMMASCOPE-RES-16K
    6. 1944
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to geometry and algebraic varieties

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

    mathematical notation and formal algebraic geometry terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.51
    ActionCreators
    -0.43
    ContextCompat
    -0.42
    DllImport
    -0.40
    libft
    -0.38
    formik
    -0.38
     Drapeau
    -0.37
    gäng
    -0.37
     Venom
    -0.35
    Venom
    -0.33
    POSITIVE LOGITS
     InputDecoration
    0.57
    PMailer
    0.56
     projective
    0.52
    astéro
    0.50
    SBATCH
    0.43
     horticultural
    0.43
     llorar
    0.42
     обез
    0.42
    asteroide
    0.42
     desnuda
    0.42
    Activations Density 1.335%

    No Known Activations