© 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. 15067
    Prev
    Next
    INDEX
    Explanations

    phrases related to official meetings and community discussions

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

    Followed by "will"

    np_acts-logits-general · gemini-2.0-flash

    assigned caseloads resolution services

    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
     dodgy
    -0.92
     reck
    -0.85
     hardly
    -0.84
     reckon
    -0.83
     marvellous
    -0.81
    Lähteet
    -0.81
    atissimo
    -0.80
     stuff
    -0.78
     whatnot
    -0.76
     übrigens
    -0.76
    POSITIVE LOGITS
     utilizing
    1.01
     utilized
    0.96
     utilize
    0.91
     utilizes
    0.91
     prior
    0.79
     אשר
    0.73
     Utilize
    0.72
     Utilizing
    0.72
    Utili
    0.71
     می‌باشد
    0.68
    Activations Density 1.920%

    No Known Activations