© 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. 28-GEMMASCOPE-RES-16K
    11. 3538
    Prev
    Next
    INDEX
    Explanations

    references to significant locations and structures in global contexts

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

    Followed by a quantity or size descriptor

    np_acts-logits-general · gemini-2.0-flash

    largest, biggest, longest, oldest

    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
    monių
    -0.40
    lė
    -0.34
     varmt
    -0.31
     billeder
    -0.30
    ⓧ
    -0.30
    irmar
    -0.29
    NullCheck
    -0.29
     egne
    -0.29
     plads
    -0.29
    Citizens
    -0.29
    POSITIVE LOGITS
     largest
    1.77
    largest
    1.59
     Largest
    1.48
    Largest
    1.38
     longest
    1.27
     oldest
    1.24
     terbesar
    1.20
     biggest
    1.15
    longest
    1.12
    biggest
    1.11
    Activations Density 0.428%

    No Known Activations