© 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. 1-GEMMASCOPE-RES-16K
    6. 3322
    Prev
    Next
    INDEX
    Explanations

    instances of the suffix "ial."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleUrls
    -0.52
    toBeTruthy
    -0.41
     désolés
    -0.38
    Linq
    -0.37
    StyleSheet
    -0.35
    AddColumn
    -0.35
     povezave
    -0.35
    BigNumber
    -0.33
    Coefficient
    -0.33
    HasIndex
    -0.32
    POSITIVE LOGITS
    IAL
    0.88
    ial
    0.85
     Snapshot
    0.67
     snapshot
    0.66
    IALE
    0.65
    verwijspagina
    0.63
    snapshot
    0.60
    ially
    0.59
    transQ
    0.59
    cz
    0.59
    Activations Density 0.334%

    No Known Activations