© 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. 2-GEMMASCOPE-RES-16K
    6. 15677
    Prev
    Next
    INDEX
    Explanations

    method calls and property accesses in Java code

    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
     дописавши
    -1.07
     beginnetje
    -0.98
     GenerationType
    -0.90
    GraphicsUnit
    -0.88
     Taktlose
    -0.87
    expandindo
    -0.87
    ValueGeneration
    -0.84
    mergeFrom
    -0.81
    MigrationBuilder
    -0.79
    AndroidJUnit
    -0.78
    POSITIVE LOGITS
    TokenName
    0.46
    rücken
    0.40
    bedaan
    0.40
    влению
    0.38
    ක්
    0.37
    [
    0.36
     Riks
    0.36
    olverine
    0.36
    uksessa
    0.36
    ästi
    0.35
    Activations Density 0.110%

    No Known Activations