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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 126
    Prev
    Next
    INDEX
    Explanations

    references to film directors and directing. The neuron activates strongly for words like "directed", "director", and names of directors, as well as related terms like "co-directed", "producer", and "production". It seems to be specifically focused on identifying information about who directed or was involved in directing films or other media productions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    references to film and television directors and their work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.50
    aarrggbb
    -0.48
    internalType
    -0.42
     विश्वसनीयता
    -0.42
    bcryptjs
    -0.41
     slack
    -0.41
     ProtoMessage
    -0.40
     noqa
    -0.39
     PIM
    -0.39
    Externé
    -0.39
    POSITIVE LOGITS
     director
    0.78
     directed
    0.77
     directors
    0.75
     Directors
    0.74
    Director
    0.74
    director
    0.71
     regista
    0.71
    Directors
    0.71
     directing
    0.71
     Directed
    0.71
    Activations Density 0.114%

    No Known Activations