© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 517
    Prev
    Next
    INDEX
    Explanations

    sequential or introductory phrases in text

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

    "First" or ordinal indicators

    np_acts-logits-general · gemini-2.0-flash

    starting with "first of all"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    /**
    -0.49
     مشين
    -0.41
    ectoria
    -0.41
    DispatchToProps
    -0.40
    Ehrungen
    -0.37
    ModelAttribute
    -0.37
    +/**
    -0.36
    vdots
    -0.36
     Jeanette
    -0.35
    istan
    -0.35
    POSITIVE LOGITS
    Firstly
    0.77
     Firstly
    0.73
    まず
    0.67
    unächst
    0.66
    Primero
    0.64
    先是
    0.61
     firstly
    0.60
    First
    0.60
     First
    0.59
    首先
    0.57
    Activations Density 0.251%

    No Known Activations