Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13350
    Prev
    Next
    INDEX
    Explanations

    procedural steps in cooking recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    عود
    -0.51
    attori
    -0.49
     Playhouse
    -0.48
     Bore
    -0.47
     Dever
    -0.47
     Kruger
    -0.47
     Hak
    -0.47
     Sandbox
    -0.46
     actresses
    -0.46
     bombers
    -0.45
    POSITIVE LOGITS
    writeFieldEnd
    0.77
     stirred
    0.71
    createStatement
    0.70
     nakalista
    0.68
     AssemblyProduct
    0.66
    momix
    0.64
    VolleyError
    0.63
     Wissenschaften
    0.62
     Stir
    0.60
     directions
    0.59
    Activations Density 0.252%

    No Known Activations