© 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 EvalsExportsinterp-engineNEWAPI 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. 1617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional distress or concern for the treatment of others

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

    Commas followed by conjunctions or adverbs

    np_acts-logits-general · gemini-2.0-flash

    explaining or defining

    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
    ...
    -0.72
    ,
    -0.66
    “
    -0.65
    …
    -0.62
    .
    -0.56
    "
    -0.50
    ?
    -0.50
    「
    -0.49
    !
    -0.47
    «
    -0.46
    POSITIVE LOGITS
     czyli
    0.93
     iaitu
    0.91
     kasarigan
    0.88
     ovvero
    0.84
     Infórmanos
    0.82
     disambiguazione
    0.81
     albeit
    0.81
     valamint
    0.80
     nonché
    0.79
     HasFactory
    0.78
    Activations Density 3.460%

    No Known Activations