© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3087
    Prev
    Next
    INDEX
    Explanations

    references to additional content or related information

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

    Followed by "Related" or similar words

    np_acts-logits-general · gemini-2.0-flash

    suggests related content or more reading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципа
    -0.54
    省市镇
    -0.52
    Билгалдахарш
    -0.50
    migrationBuilder
    -0.48
     CreateTagHelper
    -0.48
     fué
    -0.43
    îtra
    -0.43
     enfans
    -0.42
    LLocation
    -0.42
    tanleria
    -0.41
    POSITIVE LOGITS
    TagMode
    0.66
     оригіналу
    0.64
    RELATED
    0.61
     [*]
    0.56
     OGSÅ
    0.55
    MathML
    0.51
    \{\\
    0.47
     Вікіпе
    0.47
    Javadoc
    0.44
    RTGC
    0.42
    Activations Density 0.130%

    No Known Activations