© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9042
    Prev
    Next
    INDEX
    Explanations

    words related to a specific technology or file formats, particularly concerning software like Flash and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eldridge
    -0.77
     Elbe
    -0.76
     Filip
    -0.76
     CID
    -0.76
     matière
    -0.75
     Bingham
    -0.74
    bei
    -0.73
    Holt
    -0.72
     Solano
    -0.71
    entities
    -0.71
    POSITIVE LOGITS
     Sw
    1.71
    sw
    1.61
    Sw
    1.56
     sw
    1.45
     SW
    1.39
     Swain
    1.28
    SW
    1.27
     sworn
    1.22
     Swar
    1.18
     Swanson
    1.17
    Activations Density 0.107%

    No Known Activations