© 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. 41-GEMMASCOPE-RES-16K
    11. 6463
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to various hobbies and interests, particularly in cooking, gaming, food, and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档
    -0.52
    SourceChecksum
    -0.39
    CodedInputStream
    -0.39
     BitmapFactory
    -0.39
    ReusableCell
    -0.39
     MainAxisSize
    -0.37
    PhysRevLett
    -0.35
     arşivlendi
    -0.35
    뀐
    -0.34
    原始内容
    -0.34
    POSITIVE LOGITS
     fan
    1.16
     fanatic
    1.07
     lover
    1.02
     enthusiast
    1.02
     junk
    1.01
     addict
    0.98
    fan
    0.96
     afic
    0.94
     Fan
    0.93
     fanatics
    0.92
    Activations Density 0.379%

    No Known Activations