© 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. 9-GEMMASCOPE-RES-16K
    6. 7710
    Prev
    Next
    INDEX
    Explanations

    references to users and interactions in a social or digital context

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

    Text from French-speaking chat rooms

    np_acts-logits-general · gemini-2.0-flash

    greetings and technical terms

    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
    +#+#
    -0.59
    Vidite
    -0.59
    ReusableCell
    -0.58
     >=",
    -0.55
     surla
    -0.55
    
    -0.54
    rungsseite
    -0.50
     Italijanski
    -0.48
    帖最后由
    -0.48
    fromnode
    -0.46
    POSITIVE LOGITS
    interopRequire
    0.46
     <<<<<<<<<<<<<<
    0.39
    momix
    0.38
    ༉
    0.36
     Domínguez
    0.35
    škas
    0.35
     Ufer
    0.34
    ękuję
    0.34
    sikan
    0.34
     ApiException
    0.34
    Activations Density 0.428%

    No Known Activations