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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8323
    Prev
    Next
    INDEX
    Explanations

    elements related to copyright and versioning

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

    Objective-C code, specifically imports

    np_acts-logits-general · gemini-2.0-flash

    constructor `: base(` usage

    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
     "
    -0.62
     
    -0.57
     '
    -0.57
    '
    -0.55
     Bu
    -0.53
     bu
    -0.53
     dom
    -0.52
    (
    -0.51
    g
    -0.51
     $
    -0.51
    POSITIVE LOGITS
    ValueStyle
    8.23
    SequentialGroup
    1.59
    rungsseite
    1.56
    SourceChecksum
    1.53
    EndInit
    1.44
    ContentAsync
    1.43
     disambiguazione
    1.36
    abestanden
    1.35
     للاسماء
    1.34
    MigrationBuilder
    1.34
    Activations Density 0.003%

    No Known Activations