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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109694
    Prev
    Next
    INDEX
    Explanations

    references to owls or owl-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     owl
    -1.77
     Owl
    -1.66
     owls
    -1.47
    Owl
    -1.47
    owl
    -1.39
     Owls
    -1.23
     OWL
    -1.22
    OWL
    -1.15
    🦉
    -0.73
    Ow
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    0.54
    PickerController
    0.49
    LogFactory
    0.48
     Indes
    0.46
    Configurable
    0.45
     ContentValues
    0.44
    daction
    0.44
     StringTokenizer
    0.44
    CodeAttribute
    0.43
     Cases
    0.43
    Activations Density 0.001%

    No Known Activations