© 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. 8-GEMMASCOPE-RES-16K
    6. 4056
    Prev
    Next
    INDEX
    Explanations

    structured data types and attributes that describe entities in a database context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.93
    WireFormatLite
    -0.87
    Personendaten
    -0.83
    HtmlAttribute
    -0.81
    NameInMap
    -0.81
     */;
    -0.78
     CreateTagHelper
    -0.78
    InjectAttribute
    -0.78
     &___
    -0.75
     ModelExpression
    -0.71
    POSITIVE LOGITS
    rač
    0.52
    ticum
    0.52
     kertas
    0.50
     Spon
    0.48
    qDebug
    0.48
    imetsu
    0.48
    InstanceState
    0.47
     original
    0.46
    shutil
    0.45
     previous
    0.44
    Activations Density 0.125%

    No Known Activations