© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 16062
    Prev
    Next
    INDEX
    Explanations

    aspects of personal relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.70
    #+#
    -0.68
     }}$}
    -0.66
     defaultstate
    -0.62
    DebuggerNonUser
    -0.62
    帖最后由
    -0.62
    }{*}{
    -0.61
     resourceCulture
    -0.60
     Chriftian
    -0.59
     ―――――
    -0.58
    POSITIVE LOGITS
     whom
    0.83
    whom
    0.68
     sesama
    0.61
     fellow
    0.61
     rencontré
    0.61
     soulmate
    0.59
     love
    0.58
    love
    0.55
    Whom
    0.54
     lovely
    0.54
    Activations Density 0.101%

    No Known Activations