© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8383
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their relationships in various contexts

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

    Tokens preceding "Jr" or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    Jr. and Sr. suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    UnsafeEnabled
    -0.92
     Majefty
    -0.81
     Theſe
    -0.78
     itſelf
    -0.78
     "..\..\
    -0.77
     tartalomajánló
    -0.76
     ſhe
    -0.75
     Forumite
    -0.75
     "..\..\..\
    -0.74
     ſeveral
    -0.73
    POSITIVE LOGITS
     Jr
    2.74
     Sr
    2.12
    Jr
    2.10
     jr
    1.95
     junior
    1.92
     senior
    1.91
     Junior
    1.84
     III
    1.75
     Senior
    1.74
    senior
    1.69
    Activations Density 0.335%

    No Known Activations