© 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. 398
    Prev
    Next
    INDEX
    Explanations

    terms related to "commitments" and actions associated with submission and forgetting

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

    Words/tokens ending in "t" followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    committing/forgetting verbs

    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
    ️
    -0.73
    Geplaatst
    -0.71
    참고
    -0.64
     NgModule
    -0.62
     كومونز
    -0.62
     CreateTagHelper
    -0.62
    haria
    -0.61
    TintMode
    -0.61
    queda
    -0.60
     onAnimation
    -0.59
    POSITIVE LOGITS
    ting
    1.52
    ted
    1.49
    ters
    1.31
    tings
    1.24
    tingly
    1.01
    table
    1.01
    ter
    0.98
    tery
    0.95
    tting
    0.93
    🏻
    0.92
    Activations Density 0.322%

    No Known Activations