© 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. 22-GEMMASCOPE-RES-16K
    11. 1066
    Prev
    Next
    INDEX
    Explanations

    procedural and scientific terminology related to methods and processes in research

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

    Repetition or duplication

    np_acts-logits-general · gemini-2.0-flash

    number of times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.73
    RectangleBorder
    -0.67
    GEBURTSDATUM
    -0.65
     <<<<<<<<<<<<<<
    -0.65
    KommentareTeilen
    -0.62
    bufio
    -0.61
    حياته
    -0.61
    tagHelperRunner
    -0.60
    virons
    -0.57
    CloseOperation
    -0.57
    POSITIVE LOGITS
     twice
    2.71
    twice
    2.38
     thrice
    2.19
     multiple
    2.17
     several
    2.05
    Twice
    2.04
     Twice
    2.04
     TWICE
    1.93
    multiple
    1.91
    several
    1.88
    Activations Density 0.920%

    No Known Activations