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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10884
    Prev
    Next
    INDEX
    Explanations

    traits and characteristics of individuals in memorial or tribute contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.67
     Worse
    -0.59
     đang
    -0.58
     momentan
    -0.56
     potentially
    -0.55
    potentially
    -0.55
     ${\
    -0.55
     CURRENT
    -0.55
    currently
    -0.55
     Presumably
    -0.54
    POSITIVE LOGITS
     loved
    0.83
     always
    0.79
     happiest
    0.78
     '\\;'
    0.74
    ContentAsync
    0.72
    Loved
    0.71
    loved
    0.70
    always
    0.69
     gelieb
    0.69
     zawsze
    0.69
    Activations Density 0.078%

    No Known Activations