© 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. 4-GEMMASCOPE-RES-16K
    11. 4110
    Prev
    Next
    INDEX
    Explanations

    technical terminology and references related to statistics and research methodologies

    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
     allá
    -0.61
    ậm
    -0.60
     namelijk
    -0.56
     esimer
    -0.56
     Gästen
    -0.56
    Carrera
    -0.55
     Bellini
    -0.55
    rzez
    -0.54
    dataclass
    -0.54
    icitis
    -0.53
    POSITIVE LOGITS
     Socorro
    1.06
    OCO
    1.01
     bof
    0.99
     AOC
    0.98
    AOC
    0.97
     woll
    0.94
     AOS
    0.93
     Jod
    0.93
     Gok
    0.93
     Wod
    0.92
    Activations Density 10.250%

    No Known Activations