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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2379
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to sentencing and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnal
    -0.59
    卜
    -0.51
     Events
    -0.51
    glVertex
    -0.50
     events
    -0.50
     event
    -0.47
    getEvent
    -0.47
    localPosition
    -0.47
    Kapcsolódó
    -0.47
    event
    -0.46
    POSITIVE LOGITS
     sentencing
    1.17
     convicted
    1.14
     sentenced
    1.10
     convict
    1.06
     convicts
    0.97
     CURIAM
    0.93
     peniten
    0.89
     penjara
    0.87
     guilty
    0.86
     acquittal
    0.83
    Activations Density 0.540%

    No Known Activations