© 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. 40-GEMMASCOPE-RES-16K
    11. 6028
    Prev
    Next
    INDEX
    Explanations

    keywords related to characters and their interactions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ものは
    -0.47
    UnusedPrivate
    -0.43
    氏は
    -0.43
    者は
    -0.36
    方は
    -0.35
     adalah
    -0.35
    人は
    -0.35
    さんは
    -0.34
    是个
    -0.34
    Lähteet
    -0.32
    POSITIVE LOGITS
     during
    1.12
     while
    1.03
     throughout
    1.01
     whilst
    0.99
     before
    0.98
     whenever
    0.94
     after
    0.93
     when
    0.92
     despite
    0.90
     alongside
    0.90
    Activations Density 3.162%

    No Known Activations