© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and discussions involving measurements or quantities

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

    an approximate quantity

    np_acts-logits-general · gemini-2.0-flash

    quantity, amount, degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.52
     Dual
    -0.50
    ługość
    -0.49
    inander
    -0.49
    arela
    -0.46
    PhysRevLett
    -0.45
    iché
    -0.45
     dual
    -0.45
     Dow
    -0.44
    Dual
    -0.44
    POSITIVE LOGITS
     enough
    1.06
     more
    0.97
     almost
    0.94
    enough
    0.92
     less
    0.89
    almost
    0.89
     Enough
    0.85
     nearly
    0.84
     approximately
    0.83
     much
    0.82
    Activations Density 0.383%

    No Known Activations