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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9269
    Prev
    Next
    INDEX
    Explanations

    indicators of legal actions and mentions of cases

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

    legal case citations and court document formatting (case names, citations, dates, and legal references).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.54
     Ber
    -0.52
    the
    -0.52
     Johnson
    -0.50
     Mik
    -0.50
    fare
    -0.50
    ese
    -0.49
     Indo
    -0.49
     el
    -0.48
    r
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.97
     miniaturka
    0.78
     betweenstory
    0.78
    uxxxx
    0.77
     desmotivaciones
    0.77
     tartalomajánló
    0.77
    parsedMessage
    0.75
     nakalista
    0.72
    httphttps
    0.71
     sprüche
    0.69
    Activations Density 1.941%

    No Known Activations