© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9571
    Prev
    Next
    INDEX
    Explanations

    characteristics and qualities of experiences and venues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Personensuche
    -0.64
     كومونز
    -0.49
    ंदीखरीदारी
    -0.49
    abestanden
    -0.47
    __))
    -0.42
    EndContext
    -0.41
     poleg
    -0.40
    ніципалі
    -0.40
    AutoField
    -0.40
    RotationOrder
    -0.40
    POSITIVE LOGITS
    reactstrap
    0.44
    gante
    0.43
     الرياضيه
    0.41
     TAI
    0.39
    UINTN
    0.39
    PREC
    0.38
    Curi
    0.37
     taxonomic
    0.36
    cus
    0.36
     Weise
    0.35
    Activations Density 0.824%

    No Known Activations