© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8205
    Prev
    Next
    INDEX
    Explanations

    references to local servers, particularly relating to "localhost" and timestamps like "midnight."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dentaire
    -0.52
     Lingkungan
    -0.50
     attirer
    -0.42
     jspb
    -0.41
     néz
    -0.41
     escaleras
    -0.40
    Tä
    -0.39
    rücken
    -0.39
     âge
    -0.39
    Décès
    -0.38
    POSITIVE LOGITS
     midnight
    0.68
     conceptual
    0.67
     Conceptual
    0.64
    mus
    0.62
     minus
    0.60
     Midnight
    0.58
    Conceptual
    0.57
     bes
    0.56
    midnight
    0.56
     Bre
    0.56
    Activations Density 0.513%

    No Known Activations