© 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. 20-GEMMASCOPE-RES-16K
    6. 5178
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" in various contexts indicating pioneering achievements or notable distinctions

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

    phrases emphasizing being "first" or pioneering achievements in various contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ArrowToggle
    -0.37
     Fis
    -0.37
     spare
    -0.34
    ipheral
    -0.33
     stink
    -0.33
     itinéraires
    -0.33
    Kaieteur
    -0.33
    Fis
    -0.32
     Coulson
    -0.32
     their
    -0.32
    POSITIVE LOGITS
     Италијани
    0.53
     Normdatei
    0.48
     ddelweddau
    0.47
     мәкал
    0.47
     Nadie
    0.47
     intptr
    0.46
     الحره
    0.46
    msgTypes
    0.45
    новништво
    0.44
    Nadie
    0.44
    Activations Density 0.146%

    No Known Activations