© 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. 15658
    Prev
    Next
    INDEX
    Explanations

    references to technical processes and terms related to biology and development

    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
    Попис
    -0.64
     везе
    -0.52
    PyExc
    -0.50
    Sziasztok
    -0.48
    دانشنامهٔ
    -0.48
     esternos
    -0.48
    WriteAttribute
    -0.47
     postIndex
    -0.45
    Models
    -0.44
    发表于
    -0.44
    POSITIVE LOGITS
    awtextra
    0.84
    :✨
    0.68
    :+:
    0.66
     devriez
    0.61
    ighborhood
    0.60
     cracked
    0.58
    UAWEI
    0.56
    sterious
    0.56
     通販
    0.55
    hood
    0.55
    Activations Density 2.536%

    No Known Activations