© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2384
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to judicial proceedings

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

    references to institutional systems like legal, educational, or criminal justice systems.

    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
     nakalista
    -0.84
    ftagPool
    -0.81
    rawDesc
    -0.79
    Personendaten
    -0.79
     Signalez
    -0.78
    Vidite
    -0.75
     MainAxisSize
    -0.75
    bootstrapcdn
    -0.74
    تقاوى
    -0.72
    WriteTagHelper
    -0.71
    POSITIVE LOGITS
     those
    0.35
     when
    0.35
     they
    0.35
    those
    0.34
     that
    0.34
    ğiniz
    0.33
     as
    0.32
     (
    0.32
    when
    0.31
     resulting
    0.31
    Activations Density 0.607%

    No Known Activations