© 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. 5279
    Prev
    Next
    INDEX
    Explanations

    documented cases of crime and justice, particularly involving specific individuals and forensic evidence

    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
     kasarigan
    -0.61
    estino
    -0.49
    ellino
    -0.48
     Fresno
    -0.47
     mad
    -0.47
    stoy
    -0.46
    chak
    -0.45
    %");
    -0.45
     welcome
    -0.45
    currentItem
    -0.44
    POSITIVE LOGITS
    UnusedPrivate
    0.88
     مشين
    0.84
     ویکی‌پدی
    0.82
    IntoConstraints
    0.81
    WebVitals
    0.81
     Administrativna
    0.76
    IsContent
    0.74
     defaultstate
    0.73
     Roskov
    0.73
     estekak
    0.72
    Activations Density 0.655%

    No Known Activations