© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6962
    Prev
    Next
    INDEX
    Explanations

    sentences that describe processes or steps and emphasize examples

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

    Sentences containing "it was" or "it will"

    np_acts-logits-general · gemini-2.0-flash

    past establishments and examples

    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
    ItemBackground
    -0.86
     AssemblyVersion
    -0.74
     Italijani
    -0.73
    OGND
    -0.71
    ⤹
    -0.67
     мәкал
    -0.66
    NameInMap
    -0.63
    ArrowToggle
    -0.62
     Administrativna
    -0.61
     defaultstate
    -0.59
    POSITIVE LOGITS
    UnusedPrivate
    0.36
    ,
    0.32
    There
    0.31
    However
    0.29
     iconLine
    0.29
    Specifically
    0.29
    ondas
    0.28
    nt
    0.28
    :
    0.27
     remplacer
    0.26
    Activations Density 0.767%

    No Known Activations