© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2611
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their competitive performances

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

    sports match results and tournament outcomes with scores and team names.

    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
     createState
    -0.45
    ⟬
    -0.45
    postsleuth
    -0.45
    Flux
    -0.40
    flux
    -0.39
    MPS
    -0.38
    everyday
    -0.38
    Everyday
    -0.38
     flux
    -0.38
    一动
    -0.37
    POSITIVE LOGITS
     Komunikasi
    0.54
     offensively
    0.52
     Económica
    0.48
     mathematically
    0.47
    glTex
    0.47
     playoffs
    0.46
     offensive
    0.46
     CreateTagHelper
    0.46
     Sheriff
    0.45
    Sheriff
    0.43
    Activations Density 0.054%

    No Known Activations