© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105675
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'head' or 'head-related' topics, including various usages and phrases associated with the head or headaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.56
    BufferException
    -0.56
    URLException
    -0.52
    PMI
    -0.51
     Algo
    -0.51
     betweenstory
    -0.50
    vismo
    -0.50
     فريبيس
    -0.50
    igurumi
    -0.50
    orghini
    -0.49
    POSITIVE LOGITS
    Head
    1.38
    head
    1.33
     Head
    1.30
     head
    1.27
     HEAD
    1.20
    HEAD
    1.14
     heads
    1.05
    heads
    1.02
     Heads
    0.98
    Heads
    0.96
    Activations Density 0.023%

    No Known Activations