© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9802
    Prev
    Next
    INDEX
    Explanations

    references to the number two and its associations in various contexts

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

    Followed by "two"

    np_acts-logits-general · gemini-2.0-flash

    pairs of things

    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
     flere
    -0.60
     facie
    -0.57
     webbplats
    -0.56
     flera
    -0.54
     diputado
    -0.54
     berço
    -0.54
     âmes
    -0.51
     mourut
    -0.51
     hemsida
    -0.51
     meerdere
    -0.50
    POSITIVE LOGITS
     remaining
    0.94
    remaining
    0.89
    iniest
    0.85
     Roskov
    0.83
    iest
    0.81
     aforementioned
    0.78
     kasarigan
    0.78
     oldest
    0.76
     poorest
    0.76
    AutoScaleMode
    0.76
    Activations Density 0.228%

    No Known Activations