© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7788
    Prev
    Next
    INDEX
    Explanations

    references related to Facebook accounts and verification processes

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

    followed by "Facebook" or "privat"

    np_acts-logits-general · gemini-2.0-flash

    Facebook and privacy terms

    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
    多的
    -0.39
    上的
    -0.36
     sans
    -0.36
     कोई
    -0.36
    间的
    -0.35
     yes
    -0.35
    <table>
    -0.35
     sure
    -0.34
    所有的
    -0.34
     the
    -0.33
    POSITIVE LOGITS
    IsMutable
    0.93
     ویکی‌پدی
    0.92
    StructEnd
    0.90
     ब्रेकडाउन
    0.87
    awtextra
    0.84
    ValueStyle
    0.83
    MessageOf
    0.80
     otomatig
    0.78
    ViewImports
    0.77
    adaptiveStyles
    0.75
    Activations Density 0.050%

    No Known Activations