© 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. 15-GEMMASCOPE-RES-16K
    11. 2013
    Prev
    Next
    INDEX
    Explanations

    discussions of personal struggles and revelations regarding purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    horabuena
    -0.72
     oggi
    -0.71
     actuelles
    -0.70
     actuellement
    -0.69
     σήμερα
    -0.68
     dziś
    -0.66
     dzisiaj
    -0.66
     vandaag
    -0.64
    cephala
    -0.64
    andaag
    -0.64
    POSITIVE LOGITS
     hadn
    1.09
     had
    0.89
     seemed
    0.86
     would
    0.78
     wasn
    0.76
    seemed
    0.76
    ıyordu
    0.76
     havia
    0.74
    Wasn
    0.72
     habían
    0.71
    Activations Density 0.837%

    No Known Activations