© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4151
    Prev
    Next
    INDEX
    Explanations

    contexts involving medical and health-related exclusions or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.63
     RIPRODUZIONE
    -0.61
    stateProvider
    -0.58
    DockStyle
    -0.58
    makeConstraints
    -0.58
    MessageTagHelper
    -0.56
    ChildScrollView
    -0.56
    aarrggbb
    -0.54
    multer
    -0.54
    مصادر
    -0.53
    POSITIVE LOGITS
    <bos>
    0.79
     égard
    0.58
    $_['
    0.57
     _("
    0.56
    raisemb
    0.52
    cipar
    0.50
    respective
    0.50
     newVal
    0.50
    [toxicity=0]
    0.49
     onCancelled
    0.49
    Activations Density 1.050%

    No Known Activations