© 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. 5901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or contrast

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

    "so", "as", or similar comparatives

    np_acts-logits-general · gemini-2.0-flash

    "so as well as" comparison

    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
     المعيارى
    -0.63
     Eas
    -0.50
    GEBURTS
    -0.50
    цездатний
    -0.48
    السكان
    -0.47
     صوتيه
    -0.47
     Eel
    -0.46
    исленность
    -0.45
    Havolalar
    -0.44
     MES
    -0.44
    POSITIVE LOGITS
     ebenso
    0.91
     genauso
    0.81
     same
    0.72
     liksom
    0.71
     Ditto
    0.70
    same
    0.70
     along
    0.69
     Ebenso
    0.69
    Ditto
    0.69
     stejně
    0.69
    Activations Density 0.279%

    No Known Activations