© 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. 2-GEMMASCOPE-RES-16K
    11. 4874
    Prev
    Next
    INDEX
    Explanations

    numerical references, particularly related to counts and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pektive
    -0.63
     Mucha
    -0.61
    vency
    -0.59
    Hozzáférés
    -0.56
     mouseClicked
    -0.56
    homonymie
    -0.55
     propOrder
    -0.54
    ÓS
    -0.54
    kuuta
    -0.54
     resourceCulture
    -0.53
    POSITIVE LOGITS
    PreferredItem
    0.69
    ChildScrollView
    0.63
    makeText
    0.61
     fewer
    0.58
    UserScript
    0.57
    RUnlock
    0.56
    UnusedPrivate
    0.55
     many
    0.55
     several
    0.54
    ureusement
    0.53
    Activations Density 0.511%

    No Known Activations