© 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. 38-GEMMASCOPE-RES-16K
    11. 13564
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or entities involved in situations of conflict or legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -1.02
     is
    -1.01
     resemble
    -0.80
     require
    -0.79
     provide
    -0.78
     has
    -0.76
     occur
    -0.74
     serve
    -0.71
     happen
    -0.71
     exist
    -0.70
    POSITIVE LOGITS
     were
    1.41
    Were
    1.02
     Were
    1.00
    were
    0.99
     serem
    0.92
     byli
    0.90
     waren
    0.90
     були
    0.87
     erano
    0.87
     fossero
    0.85
    Activations Density 0.624%

    No Known Activations