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. 16-GEMMASCOPE-RES-16K
    6. 12108
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to legislative changes and criminal justice

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

    alteration or modification

    np_acts-logits-general · gemini-2.0-flash

    change and detection of changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useAuth
    -0.65
    endforeach
    -0.59
    CloseHandle
    -0.58
    
    -0.57
     sepol
    -0.56
     casts
    -0.55
    ѯ
    -0.55
    yarnpkg
    -0.54
     متعلقه
    -0.54
    +#+#
    -0.54
    POSITIVE LOGITS
     change
    1.50
     changes
    1.46
    change
    1.29
     changement
    1.28
     Change
    1.23
    changes
    1.23
     Changes
    1.22
    Change
    1.21
     changements
    1.19
    Changes
    1.16
    Activations Density 1.351%

    No Known Activations