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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16317
    Prev
    Next
    INDEX
    Explanations

    specific structured data formats or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, names, and math symbols

    np_acts-logits-general · gemini-2.0-flash

    names, titles, or archaic terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngOnInit
    -0.50
    TestBed
    -0.50
    ])))
    -0.48
    ()))
    
    -0.45
    "]);
    
    -0.44
    xmlhttp
    -0.43
    "]))
    -0.43
    őre
    -0.43
    思い
    -0.43
    ))))
    -0.43
    POSITIVE LOGITS
    nameof
    0.87
    ſelf
    0.86
     AssemblyTitle
    0.85
     nameof
    0.84
     Jefus
    0.80
     Efq
    0.80
     ſeveral
    0.80
     houſe
    0.78
     ſtand
    0.78
    出版年
    0.77
    Activations Density 0.360%

    No Known Activations