© 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. 40-GEMMASCOPE-RES-16K
    6. 1528
    Prev
    Next
    INDEX
    Explanations

    familiarity with romantic comedy themes and character dynamics

    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
     Gewalt
    -0.48
    yttä
    -0.47
     steampunk
    -0.45
     violento
    -0.45
     Warhammer
    -0.45
    ukone
    -0.45
     döv
    -0.44
     puisi
    -0.44
     Assassin
    -0.44
     poésie
    -0.44
    POSITIVE LOGITS
     sitcom
    0.61
     comedies
    0.60
     rom
    0.57
     comedy
    0.56
     estekak
    0.54
     hilarious
    0.53
     lovable
    0.53
     hil
    0.52
     wacky
    0.51
     funniest
    0.51
    Activations Density 0.307%

    No Known Activations