© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6535
    Prev
    Next
    INDEX
    Explanations

    references to ordinal numerals or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.83
    er
    -0.82
    ed
    -0.77
    ']):
    -0.71
    ey
    -0.68
    aluz
    -0.66
    εί
    -0.65
    eo
    -0.65
    ;'>
    -0.63
     Neu
    -0.63
    POSITIVE LOGITS
     Firth
    0.97
    tenth
    0.92
     Tenth
    0.88
    ptonshire
    0.86
    th
    0.83
     Seventh
    0.83
    Matth
    0.83
    sixth
    0.81
     tenths
    0.81
    LLocation
    0.80
    Activations Density 0.092%

    No Known Activations