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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 2780
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to internet connectivity and network operations

    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
    UnsafeEnabled
    -0.85
    rungsseite
    -0.81
    orianCalendar
    -0.72
    MessageOf
    -0.70
    ANTLR
    -0.69
    writeFieldEnd
    -0.68
     ProtoMessage
    -0.68
    มาะ
    -0.67
    ValueStyle
    -0.67
     Préférences
    -0.66
    POSITIVE LOGITS
     internet
    2.09
     Internet
    1.95
     WiFi
    1.77
    internet
    1.74
     wifi
    1.73
    Internet
    1.73
     Wi
    1.69
     Wifi
    1.57
     INTERNET
    1.55
     WIFI
    1.53
    Activations Density 0.162%

    No Known Activations