© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6742
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court findings and evidence

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

    "Is/are" followed by a word indicating support or lack thereof

    np_acts-logits-general · gemini-2.0-flash

    legal arguments and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angliski
    -0.68
    <!--[
    -0.64
    ImageContext
    -0.60
    Hozzáférés
    -0.58
    styleType
    -0.57
    Personendaten
    -0.56
    نسية
    -0.56
    IntoConstraints
    -0.56
     замо
    -0.55
     Dostupné
    -0.55
    POSITIVE LOGITS
    AutoScale
    0.62
     propOrder
    0.56
     legal
    0.54
     légal
    0.54
     legales
    0.53
    MigrationBuilder
    0.51
    legal
    0.50
     geboten
    0.50
     legally
    0.48
    struzione
    0.48
    Activations Density 2.341%

    No Known Activations