© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1238
    Prev
    Next
    INDEX
    Explanations

    the presentation of arguments related to legal claims and due process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ství
    -0.60
    перь
    -0.59
    følgelig
    -0.56
    OOTDTY
    -0.56
    undred
    -0.56
     ComVisible
    -0.56
    ousands
    -0.55
    èdent
    -0.55
    ̓
    -0.54
    brou
    -0.54
    POSITIVE LOGITS
     []:
    0.91
     مشين
    0.78
    RegressionTest
    0.75
    IVEREF
    0.64
    __*/
    0.64
    RefNanny
    0.61
    xtext
    0.61
     pygame
    0.60
    memoized
    0.59
     Inverness
    0.59
    Activations Density 0.130%

    No Known Activations