© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11485
    Prev
    Next
    INDEX
    Explanations

    references to specific communities or subcultures

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

    Followed by "user"

    np_acts-logits-general · gemini-2.0-flash

    endings like 'arians' or 'eks'

    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
    toprule
    -0.33
     Instruments
    -0.31
     STRESS
    -0.30
     thái
    -0.30
     instruments
    -0.30
     Stress
    -0.29
    rot
    -0.29
     INPUTS
    -0.28
    mean
    -0.28
     stress
    -0.28
    POSITIVE LOGITS
     Comprometido
    0.68
     CanadaChoose
    0.66
    PreferredItem
    0.60
     للمعارف
    0.58
    rungsseite
    0.54
    WEBPACK
    0.54
    transQ
    0.54
    igshid
    0.53
    Pranala
    0.53
     aficionados
    0.53
    Activations Density 0.266%

    No Known Activations