© 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. 11-GEMMASCOPE-RES-16K
    6. 14553
    Prev
    Next
    INDEX
    Explanations

    health-related terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tesy
    -0.67
     TRACE
    -0.56
    titus
    -0.55
    minent
    -0.54
     Marcell
    -0.53
    mittances
    -0.53
    SnackBar
    -0.52
    enumii
    -0.52
    sunter
    -0.52
    ouret
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.76
     helst
    0.59
    yntaxException
    0.57
    ArgsConstructor
    0.55
     NSCoder
    0.54
     ModelExpression
    0.49
     happiest
    0.48
    gonic
    0.48
    InputBorder
    0.48
    IBOutlet
    0.48
    Activations Density 0.315%

    No Known Activations