© 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. 35-GEMMASCOPE-RES-16K
    11. 14533
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal documentation and formal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    舺
    -0.34
     Being
    -0.32
     unterwegs
    -0.31
    ustice
    -0.31
     gian
    -0.30
     Effectiveness
    -0.30
    bison
    -0.29
    TableAdapter
    -0.29
    BuildContext
    -0.29
     autant
    -0.29
    POSITIVE LOGITS
     describing
    1.66
     detailing
    1.56
     indicating
    1.55
     explaining
    1.52
     outlining
    1.50
     depicting
    1.48
     announcing
    1.41
     stating
    1.39
     showing
    1.37
     denoting
    1.35
    Activations Density 2.202%

    No Known Activations