© 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. 31-GEMMASCOPE-RES-16K
    11. 3571
    Prev
    Next
    INDEX
    Explanations

    details about films, including their titles, directors, release dates, and synopses

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

    This neuron activates strongly on the word "film" and common associated terms like "was," "is," and "It" that typically appear in film descriptions and synopses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лтемелер
    -0.46
    CloseOperation
    -0.46
    ILayout
    -0.41
     Infórmanos
    -0.37
    حوالہ
    -0.36
     привы
    -0.35
    protoimpl
    -0.35
    npmjs
    -0.33
    朱印
    -0.32
    bootstrapcdn
    -0.32
    POSITIVE LOGITS
     starring
    1.20
     featuring
    1.19
    featuring
    1.06
    Featuring
    0.97
     Featuring
    0.95
    Starring
    0.93
     Starring
    0.91
     depicting
    0.84
     protagon
    0.84
     filmed
    0.78
    Activations Density 0.303%

    No Known Activations