© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2603
    Prev
    Next
    INDEX
    Explanations

    URLs and references to internet resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -1.18
    WithIOException
    -1.08
    httphttps
    -1.05
     صوتيه
    -1.04
    RenderAtEndOf
    -1.03
    oredCriteria
    -0.99
     متعلقه
    -0.98
    TypedDataSet
    -0.98
    migrationBuilder
    -0.95
     Roskov
    -0.94
    POSITIVE LOGITS
    en
    0.54
     English
    0.51
     zh
    0.45
    ња
    0.43
    ENGLISH
    0.42
    English
    0.41
     ENGLISH
    0.40
     fr
    0.38
     en
    0.38
    english
    0.37
    Activations Density 0.446%

    No Known Activations