Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2324
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and definitions of negligence

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

    Legal proceedings and arguments

    np_acts-logits-general · gemini-2.0-flash

    legal parties and proceedings

    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
    LikeLike
    -0.56
     associées
    -0.52
     nutzen
    -0.52
     encor
    -0.51
     effray
    -0.51
     découver
    -0.51
    {}/
    -0.50
    FormState
    -0.50
     sauvages
    -0.50
     dévelo
    -0.50
    POSITIVE LOGITS
     *
    0.82
     "*
    0.80
     defendant
    0.78
     appellant
    0.74
    Personensuche
    0.73
     paroi
    0.72
    ConstraintMaker
    0.71
     plaintiff
    0.70
     appellants
    0.67
     appellee
    0.65
    Activations Density 4.223%

    No Known Activations