© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12571
    Prev
    Next
    INDEX
    Explanations

    references to "other" entities or categories, particularly related to evidence or groups of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     másik
    -0.41
     المعيارى
    -0.41
    PhysRevD
    -0.40
     الحره
    -0.40
     diğer
    -0.39
    IntoConstraints
    -0.37
     itſelf
    -0.37
     inaczej
    -0.36
    ︎
    -0.36
     other
    -0.35
    POSITIVE LOGITS
    worldly
    1.19
     than
    0.80
     niż
    0.71
     THAN
    0.63
     decât
    0.59
     similarly
    0.57
     kuin
    0.57
    similar
    0.56
     kinds
    0.56
    world
    0.56
    Activations Density 0.239%

    No Known Activations