© 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. 14-GEMMASCOPE-RES-16K
    6. 11159
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with identifiers or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.97
    addContainerGap
    -0.82
    ContentAsync
    -0.79
    AnimationsModule
    -0.73
    نیم
    -0.73
    ValueStyle
    -0.72
     hObject
    -0.71
     مشين
    -0.71
    RegistryLite
    -0.70
    énario
    -0.70
    POSITIVE LOGITS
     
    0.60
    ()[
    0.49
    <bos>
    0.48
     esternos
    0.47
    اریخ
    0.45
    )['
    0.44
     listOf
    0.43
    <_
    0.43
    ه‌
    0.43
    ⇌
    0.43
    Activations Density 0.083%

    No Known Activations