© 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. 18-GEMMASCOPE-RES-16K
    11. 9808
    Prev
    Next
    INDEX
    Explanations

    HTML tag structures and their attributes

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

    HTML or code attributes

    np_acts-logits-general · gemini-2.0-flash

    HTML metadata and descriptions

    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
     named
    -0.92
     Named
    -0.87
    Named
    -0.81
     name
    -0.76
     Name
    -0.75
    named
    -0.75
     nommé
    -0.74
    Titled
    -0.73
    Name
    -0.72
     naming
    -0.70
    POSITIVE LOGITS
     description
    0.67
    getDescription
    0.66
    description
    0.65
    setDescription
    0.60
     sous
    0.60
    Géographie
    0.58
    adaptiveStyles
    0.56
    サブ
    0.56
     brevi
    0.55
     descrit
    0.55
    Activations Density 0.201%

    No Known Activations