© 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. 5860
    Prev
    Next
    INDEX
    Explanations

    technical elements related to coding structures and libraries

    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
     seul
    -0.57
    ρεύ
    -0.56
    alyse
    -0.52
     Chien
    -0.51
    attendre
    -0.50
    bno
    -0.50
    irmar
    -0.49
    PLACEMENT
    -0.49
     vorbehalten
    -0.48
     Ors
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.70
     Ep
    0.70
     wounds
    0.68
     Wound
    0.68
     wound
    0.67
    Wound
    0.67
     ep
    0.66
    EP
    0.65
    ="@+
    0.65
    WriteLiteral
    0.64
    Activations Density 2.863%

    No Known Activations