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. 21-GEMMASCOPE-RES-16K
    6. 6497
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to criminal charges and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.66
    DeleteBehavior
    -0.58
     Paglinawan
    -0.57
    ernoo
    -0.53
    awtextra
    -0.52
    oredCriteria
    -0.52
     CanadaChoose
    -0.50
    BeginContext
    -0.50
     ISNI
    -0.49
    inSlope
    -0.48
    POSITIVE LOGITS
     sentenced
    0.76
     felony
    0.71
     criminal
    0.71
     prison
    0.70
     jail
    0.69
     convicted
    0.68
     sentencing
    0.63
     incarceration
    0.59
     jailed
    0.58
     crime
    0.57
    Activations Density 1.645%

    No Known Activations