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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4827
    Prev
    Next
    INDEX
    Explanations

    nothing, as it has no significant activations

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

    Non-alphanumeric characters and the following word

    np_acts-logits-general · gemini-2.0-flash

    sequences following specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TintMode
    -0.79
    
    -0.78
     שוליים
    -0.78
     houſe
    -0.77
    ArrowToggle
    -0.76
     '\\;'
    -0.76
     fubject
    -0.75
     Houſe
    -0.73
     Efq
    -0.72
     iſt
    -0.72
    POSITIVE LOGITS
    </blockquote>
    0.46
    optarg
    0.46
     cinque
    0.42
     náv
    0.42
    strftime
    0.41
    eni
    0.40
     le
    0.40
     grand
    0.40
     BufferedReader
    0.39
    ota
    0.39
    Activations Density 0.015%

    No Known Activations