© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8165
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure in the text

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

    HTML title tag, title, and title-like words

    np_acts-logits-general · gemini-2.0-flash

    html title tags and headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unknownFields
    -0.46
    Chham
    -0.45
    IntentFilter
    -0.39
     konser
    -0.39
    FlatAppearance
    -0.37
     voorbeeld
    -0.36
     penumpang
    -0.36
    uspiel
    -0.36
     nonUne
    -0.35
     paliwa
    -0.35
    POSITIVE LOGITS
     title
    1.38
    title
    1.13
     Title
    1.12
     titles
    1.07
     título
    1.07
    Title
    1.05
     getTitle
    1.03
     TITLE
    1.03
    标题
    0.98
     titel
    0.98
    Activations Density 0.328%

    No Known Activations