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

    Neuronpedia

    Jacobian LensNEW
    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. 9717
    Prev
    Next
    INDEX
    Explanations

    inquiries and requests for information

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

    Preceding "something" or "over"

    np_acts-logits-general · gemini-2.0-flash

    searching for something specific or missing

    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
    @@@@@
    -0.44
    Viki
    -0.36
    stacked
    -0.35
    layered
    -0.35
    heri
    -0.33
    fucking
    -0.33
    caref
    -0.33
    vertido
    -0.33
     vient
    -0.33
    回事
    -0.31
    POSITIVE LOGITS
     particularmente
    0.69
     particular
    0.69
     particularly
    0.68
     particolari
    0.66
     missing
    0.66
     PARTICULAR
    0.66
     unexpected
    0.63
     besonders
    0.61
     particolarmente
    0.61
     المعيارى
    0.61
    Activations Density 0.416%

    No Known Activations