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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9614
    Prev
    Next
    INDEX
    Explanations

    key elements of behind-the-scenes production and storytelling in television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.46
     geslacht
    -0.45
     scienza
    -0.44
    Derbyniad
    -0.43
    formatics
    -0.43
    bitField
    -0.43
    webElement
    -0.41
     raccomand
    -0.41
     peintre
    -0.40
     letteratura
    -0.39
    POSITIVE LOGITS
     episode
    1.05
     episodes
    0.82
     Episode
    0.81
    episode
    0.75
     chapter
    0.75
    Episode
    0.73
     episódio
    0.66
     Episodes
    0.65
     épisode
    0.65
     episodio
    0.64
    Activations Density 0.336%

    No Known Activations