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. 14656
    Prev
    Next
    INDEX
    Explanations

    elements related to personal purpose and introspection

    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
    CloseOperation
    -0.59
     betweenstory
    -0.53
     مرئيه
    -0.52
    tagext
    -0.50
    PerformLayout
    -0.50
    SequentialGroup
    -0.50
     purpoſe
    -0.50
    
    -0.49
     erſt
    -0.49
    Уважаемые
    -0.48
    POSITIVE LOGITS
     READ
    0.63
    Related
    0.61
     RELATED
    0.61
    RELATED
    0.61
     Related
    0.61
    READ
    0.58
    SEE
    0.54
     SEE
    0.52
     related
    0.50
     Image
    0.50
    Activations Density 0.202%

    No Known Activations