© 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. 13-GEMMASCOPE-RES-16K
    6. 6911
    Prev
    Next
    INDEX
    Explanations

    email addresses and related contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.68
    enterOuterAlt
    -0.62
     surla
    -0.60
     onCreateView
    -0.59
    WindowConstants
    -0.58
     VizieR
    -0.58
     octaves
    -0.57
     vulgaires
    -0.56
     chert
    -0.56
    Халык
    -0.56
    POSITIVE LOGITS
    mailto
    1.16
     email
    0.93
    Email
    0.84
     Email
    0.83
     emails
    0.82
     mail
    0.81
    email
    0.79
     emailing
    0.78
     EMAIL
    0.77
    Emails
    0.75
    Activations Density 0.159%

    No Known Activations