© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 357
    Prev
    Next
    INDEX
    Explanations

    attribute names and properties in structured data formats like XML, JSON, or programming code.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    coding elements and structures within programming contexts

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

    HTML or XML attributes/properties

    np_acts-logits-general · gemini-2.0-flash

    keys and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     desmotivaciones
    -0.60
     queſta
    -0.58
     eşofman
    -0.58
    MemoryWarning
    -0.57
     increí
    -0.57
     zoude
    -0.57
    ]")]
    -0.56
    ésultats
    -0.56
     ſondern
    -0.54
    enablog
    -0.54
    POSITIVE LOGITS
    HtmlAttribute
    0.50
    RectangleBorder
    0.44
    HeaderText
    0.41
    AndEndTag
    0.41
    SequentialGroup
    0.38
    InputTagHelper
    0.38
    ◗
    0.36
    StartTag
    0.35
     LIK
    0.35
    ">//
    0.35
    Activations Density 1.463%

    No Known Activations