© 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. 31-GEMMASCOPE-RES-16K
    11. 2435
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and formulas related to calculation and representation

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

    mathematical expressions involving equals signs and arithmetic operations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    assignment operators and mathematical expressions in code and mathematical notation.

    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
     Picchu
    -0.40
    Chham
    -0.36
     Leit
    -0.35
     Mawr
    -0.35
    ば
    -0.34
    thul
    -0.34
    éric
    -0.33
    omni
    -0.33
     IBOutlet
    -0.32
     needle
    -0.32
    POSITIVE LOGITS
     round
    1.66
     Round
    1.59
     rounding
    1.58
     rounded
    1.55
    round
    1.53
     ROUND
    1.53
    Round
    1.51
    ROUND
    1.38
    rounding
    1.29
     Rounded
    1.27
    Activations Density 0.923%

    No Known Activations