© 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. 3812
    Prev
    Next
    INDEX
    Explanations

    references to bugs or issues in a discussion or technical context

    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
    batore
    -0.50
    endphp
    -0.50
    Controllo
    -0.50
    DBNull
    -0.48
    fony
    -0.47
    atzung
    -0.46
    сию
    -0.46
    endpush
    -0.46
    Enllaces
    -0.45
    nonatomic
    -0.45
    POSITIVE LOGITS
     المعيارى
    0.60
     terecht
    0.57
     сюда
    0.57
     اینجا
    0.55
     official
    0.55
    official
    0.54
     Official
    0.54
    Official
    0.54
     general
    0.54
    EditorBrowsable
    0.53
    Activations Density 0.340%

    No Known Activations