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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11345
    Prev
    Next
    INDEX
    Explanations

    technical terms, error messages, and data types associated with computing processes

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

    "[...index]" or "[...pha]" in tables/figures

    np_acts-logits-general · gemini-2.0-flash

    index flux

    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
     besø
    -0.54
    hematical
    -0.53
    eſ
    -0.51
    maxcdn
    -0.49
    enschappe
    -0.48
    polation
    -0.48
    ffions
    -0.46
     population
    -0.46
    leſs
    -0.46
    mitive
    -0.45
    POSITIVE LOGITS
    enderror
    1.02
    complexContent
    0.75
     Exacts
    0.73
    +#+#
    0.72
     الحره
    0.71
    RTEX
    0.71
    aarrggbb
    0.70
    TagMode
    0.70
    ########.
    0.66
     متعلقه
    0.66
    Activations Density 1.257%

    No Known Activations