© 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. 18-GEMMASCOPE-RES-16K
    11. 2010
    Prev
    Next
    INDEX
    Explanations

    mentions of conferences and related events

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

    "conference"

    np_acts-logits-general · gemini-2.0-flash

    conference and associated terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <tr>
    -0.60
     resourceCulture
    -0.59
     kul
    -0.58
    qrstuvwxyz
    -0.55
    toHexString
    -0.53
    ら
    -0.53
     mol
    -0.52
    новниш
    -0.52
    PyExc
    -0.52
    mian
    -0.50
    POSITIVE LOGITS
     conferences
    1.03
     Conferences
    1.01
     conference
    0.97
     Conference
    0.96
    Conference
    0.93
     CONFERENCE
    0.89
    conference
    0.85
     houſe
    0.82
     halls
    0.80
     Konferenz
    0.79
    Activations Density 0.080%

    No Known Activations