© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15638
    Prev
    Next
    INDEX
    Explanations

    terms related to configuration settings and default values in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Default or user-specified values

    np_acts-logits-general · gemini-2.0-flash

    default or defaults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.62
    RenderAtEndOf
    -0.60
    اریخ
    -0.57
    CodedInputStream
    -0.55
    НИК
    -0.54
    IContainer
    -0.52
     postIndex
    -0.52
    findpost
    -0.50
    aimerais
    -0.50
     cherchés
    -0.49
    POSITIVE LOGITS
     default
    2.93
    default
    2.60
     Default
    2.46
     defaults
    2.38
    Default
    2.34
    默认
    2.15
     DEFAULT
    2.02
     defaulted
    1.97
    DEFAULT
    1.93
    デフォ
    1.92
    Activations Density 0.542%

    No Known Activations