© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2173
    Prev
    Next
    INDEX
    Explanations

    code structures and programming language elements

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

    HTML and code structure elements like tags, comments, and programming syntax.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intenciones
    -0.40
     domésticos
    -0.40
     contratación
    -0.39
     venganza
    -0.39
     disfraces
    -0.39
     turística
    -0.39
     doméstico
    -0.38
     mecánico
    -0.38
     promesas
    -0.38
     condena
    -0.38
    POSITIVE LOGITS
    ɵɵelementStart
    0.76
     CreateTagHelper
    0.75
    Autoritní
    0.71
    RenderAtEndOf
    0.71
    ImageContext
    0.70
    Diweddarwch
    0.68
     Roskov
    0.66
     autorytatywna
    0.63
     pinulongan
    0.63
    الحياه
    0.62
    Activations Density 0.377%

    No Known Activations