© 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. 7-GEMMASCOPE-RES-16K
    11. 15599
    Prev
    Next
    INDEX
    Explanations

    HTML link attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.71
    AndEndTag
    -0.63
    MemoryWarning
    -0.62
     Paglinawan
    -0.62
     Wikimedijinoj
    -0.60
    AndroidJUnit
    -0.60
    __(/*!
    -0.59
     <<<<<<<<<<<<<<
    -0.58
    aarrggbb
    -0.57
     المعيارى
    -0.57
    POSITIVE LOGITS
     rel
    3.75
     Rel
    3.02
    Rel
    2.89
    rel
    2.73
     REL
    2.41
    REL
    2.28
     rela
    1.69
     relati
    1.65
    rels
    1.62
    rela
    1.60
    Activations Density 0.076%

    No Known Activations