© 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. 15-GEMMASCOPE-RES-16K
    11. 9970
    Prev
    Next
    INDEX
    Explanations

    JavaScript object and array manipulation methods and their related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.56
    lern
    -0.48
    MigrationBuilder
    -0.46
     Fo
    -0.46
    JsonPropertyName
    -0.45
     '\\;'
    -0.42
    ++]
    -0.42
     noastre
    -0.42
    GetAxis
    -0.42
     мәкал
    -0.41
    POSITIVE LOGITS
     iconFacebook
    0.68
    |_{\
    0.67
    Népesség
    0.65
     tourner
    0.63
    XtraEditors
    0.59
    |_{
    0.58
    Atsauces
    0.57
     صوتيه
    0.57
     StatefulWidget
    0.56
    elemField
    0.56
    Activations Density 0.092%

    No Known Activations