© 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. 4106
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to subscriptions in programming

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

    GraphQL subscription code including "id"

    np_acts-logits-general · gemini-2.0-flash

    GraphQL IDs and repeated fields

    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
    XmlAccessType
    -0.90
     newBuilder
    -0.78
    sizeCache
    -0.74
    #+#
    -0.73
     Taktlose
    -0.73
    TypedDataSet
    -0.70
    PerformLayout
    -0.66
    >";
    -0.64
    UnsafeEnabled
    -0.63
     >=",
    -0.63
    POSITIVE LOGITS
     OMIT
    0.48
    UrlResolution
    0.47
    uxxxx
    0.46
    ftagPool
    0.44
    ults
    0.42
     GraphQL
    0.40
    __
    0.40
    ImageContext
    0.39
    ogi
    0.39
    ("__
    0.39
    Activations Density 0.626%

    No Known Activations