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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 73
    Prev
    Next
    INDEX
    Explanations

    references to legal claims and grievances within the judicial context

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

    details about jail/prison procedures and inmate interactions with correctional staff.

    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
     instalação
    -0.40
     Kräuter
    -0.38
     ingredienti
    -0.38
     professionale
    -0.38
    uttavia
    -0.38
     macetas
    -0.36
     felicidade
    -0.36
    Synonymes
    -0.36
     problemática
    -0.36
    GeoNames
    -0.35
    POSITIVE LOGITS
     inmates
    0.86
     prisoners
    0.84
     inmate
    0.81
     prisoner
    0.79
     prison
    0.79
    prison
    0.75
     Prisoners
    0.75
    Prison
    0.72
     Prison
    0.71
     detainees
    0.68
    Activations Density 0.610%

    No Known Activations