© 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. 4736
    Prev
    Next
    INDEX
    Explanations

    technical references and operations related to computational processes

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

    Variables like i, j, k in code or equations

    np_acts-logits-general · gemini-2.0-flash

    indices in mathematical expressions

    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
    IntoConstraints
    -0.40
    хьтан
    -0.28
    Weiterlesen
    -0.27
     tâ
    -0.26
    internalType
    -0.25
    trend
    -0.25
    상
    -0.25
     Acc
    -0.25
    sendLog
    -0.24
     Peace
    -0.24
    POSITIVE LOGITS
     الحره
    0.69
    ChildScrollView
    0.68
    NSIndexPath
    0.65
    addContainerGap
    0.64
     ProtoMessage
    0.59
    ReusableCell
    0.57
    astéroïdes
    0.56
     individually
    0.54
    TemporalType
    0.54
    期刊论文
    0.54
    Activations Density 1.218%

    No Known Activations