© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7060
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "of" and related phrases indicating relationships or connections

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

    "due to" followed by a reason

    np_acts-logits-general · gemini-2.0-flash

    due to, of, to

    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
    uxxxx
    -0.74
    帖最后由
    -0.68
    findpost
    -0.66
    RenderAtEndOf
    -0.59
    tilor
    -0.59
     فريبيس
    -0.57
    basicConfig
    -0.56
     وتسجيلات
    -0.56
     мәкал
    -0.54
     ProtoMessage
    -0.54
    POSITIVE LOGITS
     a
    0.42
     the
    0.42
     an
    0.40
    ":
    
    0.36
    <bos>
    0.35
     {},
    
    0.35
    躇
    0.34
     their
    0.34
     />,
    0.33
    AISSEE
    0.32
    Activations Density 0.892%

    No Known Activations