© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 50084
    Prev
    Next
    INDEX
    Explanations

    programming or mathematical syntax elements

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

    math and code structures

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron primarily detects the start-of-sequence / beginning-of-document token (i.e., the start of an input).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蚪
    -0.30
     fons
    -0.30
    pygame
    -0.28
     nomb
    -0.28
    Atsauces
    -0.27
    {/*
    -0.27
     kohdetta
    -0.27
    commented
    -0.27
    Билгалдахарш
    -0.27
     pleaſure
    -0.27
    POSITIVE LOGITS
    flashdata
    0.66
    kloped
    0.59
    remmo
    0.54
    ğum
    0.53
    IsContent
    0.53
    cula
    0.52
    ไหน
    0.51
    Ⴈ
    0.50
    cloudflare
    0.50
    <start_of_turn>
    0.50
    Activations Density 0.007%

    No Known Activations