Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12322
    Prev
    Next
    INDEX
    Explanations

    instances of historical political events and related figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.60
     BrowserModule
    -0.57
     nakalista
    -0.56
     ſche
    -0.55
     [*]
    -0.54
     Shyam
    -0.54
     censiti
    -0.48
    ſand
    -0.48
     ſta
    -0.47
     anis
    -0.47
    POSITIVE LOGITS
    ushchev
    0.56
     Eisenhower
    0.55
     Khrushchev
    0.53
    ValueStyle
    0.41
     Beatles
    0.40
     JFK
    0.38
    EndProject
    0.36
    idom
    0.36
     Nehru
    0.35
     Gaulle
    0.34
    Activations Density 1.057%

    No Known Activations