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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5253
    Prev
    Next
    INDEX
    Explanations

    legal case references and citations

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

    legal citations, specifically U.S. Supreme Court case references with volume numbers, page numbers, and citation details.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.63
     createSprite
    -0.56
     tartalomajánló
    -0.51
    ReusableCell
    -0.50
     papilla
    -0.50
    SuspendLayout
    -0.47
    icksburg
    -0.47
     Савезне
    -0.47
     politici
    -0.47
    amaño
    -0.46
    POSITIVE LOGITS
    Rptr
    1.16
     Rptr
    0.80
     nakalista
    0.54
    BeginContext
    0.54
    .*")]
    0.45
     uLocal
    0.42
    VIAF
    0.42
    findpost
    0.41
     صوتيه
    0.40
    ValueStyle
    0.37
    Activations Density 0.473%

    No Known Activations