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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 648
    Prev
    Next
    INDEX
    Explanations

    terms related to legal charges and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    enetrable
    -0.57
    TagMode
    -0.54
     protoimpl
    -0.51
    principalColumn
    -0.47
     initComponents
    -0.47
    olutamente
    -0.46
     cherchés
    -0.45
     mécan
    -0.45
    стоинства
    -0.44
    !*\
    -0.43
    POSITIVE LOGITS
     faces
    1.06
     pleaded
    1.06
     arrested
    1.03
     accused
    0.96
     confessed
    0.95
     Arrested
    0.92
     charged
    0.88
     admitted
    0.87
     sentenced
    0.87
     plead
    0.86
    Activations Density 0.460%

    No Known Activations