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. 0-GEMMASCOPE-RES-16K
    6. 9642
    Prev
    Next
    INDEX
    Explanations

    references to the Spring Framework and instances of the word "beat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -1.12
     Chwiliwch
    -1.08
     estekak
    -0.97
    enderror
    -0.95
     ExecuteAsync
    -0.94
     témoig
    -0.94
    GEBURTSDATUM
    -0.91
     NSCoder
    -0.90
    principalColumn
    -0.90
     שוליים
    -0.90
    POSITIVE LOGITS
    pop
    0.54
    low
    0.45
     beat
    0.42
     low
    0.39
    2
    0.38
     Beat
    0.38
    ↵
    0.37
    ↵↵
    0.37
    1
    0.37
     famous
    0.36
    Activations Density 0.298%

    No Known Activations