© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7304
    Prev
    Next
    INDEX
    Explanations

    forms of the word "acting" and its variations, indicating a focus on performance or portrayal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.59
     læng
    -0.55
     pescoço
    -0.55
     isolato
    -0.54
    fillType
    -0.54
     vectorielle
    -0.54
     itſelf
    -0.53
    ckså
    -0.52
     médicale
    -0.52
     partielle
    -0.52
    POSITIVE LOGITS
     VR
    0.62
     HR
    0.52
     Frank
    0.50
     competitor
    0.50
     acting
    0.48
     rival
    0.47
     Amanda
    0.46
     fantasy
    0.46
     Bj
    0.46
    VR
    0.46
    Activations Density 0.676%

    No Known Activations