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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11591
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and regulatory frameworks

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

    Tokens after specific prefixes

    np_acts-logits-general · gemini-2.0-flash

    word beginnings and endings

    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
     læ
    -0.40
    Cite
    -0.40
    AutoField
    -0.40
     is
    -0.39
    ditionally
    -0.39
    Fired
    -0.39
    ,
    -0.39
    Français
    -0.38
     or
    -0.38
     are
    -0.37
    POSITIVE LOGITS
    LookAnd
    1.00
    Personensuche
    0.86
    
    0.83
    脚注の使い方
    0.82
     فريبيس
    0.81
    ValueStyle
    0.80
     مشين
    0.79
    تقاوى
    0.78
     kaarangay
    0.77
     $_"
    0.76
    Activations Density 0.383%

    No Known Activations