© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2220
    Prev
    Next
    INDEX
    Explanations

    words that are related to emotional or experiential states

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

    ending in "ary", "ory", "ity", "edy", or "ery"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ity, ary, ory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alış
    -0.48
    følgelig
    -0.48
    woff
    -0.48
    ن
    -0.47
    m
    -0.47
    hspace
    -0.47
    «<
    -0.46
    ฒ
    -0.45
    sc
    -0.45
    en
    -0.44
    POSITIVE LOGITS
    ry
    0.87
    ety
    0.87
    tory
    0.85
    ey
    0.83
    edy
    0.82
    oty
    0.82
    y
    0.82
    ery
    0.81
    ecy
    0.81
    ady
    0.80
    Activations Density 1.690%

    No Known Activations