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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 36-GEMMASCOPE-RES-16K
    6. 11503
    Prev
    Next
    INDEX
    Explanations

    specific actions and interactions involving people and their pets in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.46
     domov
    -0.40
    XmlEnum
    -0.39
    permitAll
    -0.36
     Вікі
    -0.36
    utuhkan
    -0.36
    献
    -0.36
    Становништво
    -0.36
    imédia
    -0.35
    íncia
    -0.35
    POSITIVE LOGITS
     rush
    0.88
     trot
    0.85
     raced
    0.81
     dash
    0.81
     rushed
    0.79
     rushing
    0.79
     sprint
    0.79
     gallop
    0.78
     scur
    0.77
     rushes
    0.76
    Activations Density 0.438%

    No Known Activations