© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their roles in specific events or reports

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

    Followed by punctuation or numbers

    np_acts-logits-general · gemini-2.0-flash

    we represent, then implement

    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
    setRotation
    -0.56
     Svet
    -0.51
    voix
    -0.49
     legit
    -0.47
    itiva
    -0.47
     suck
    -0.46
    casila
    -0.46
    eaky
    -0.46
     trung
    -0.46
     sucks
    -0.45
    POSITIVE LOGITS
    BeginContext
    0.74
    nytimes
    0.65
    <tfoot>
    0.61
    Mr
    0.58
    yntaxException
    0.57
     Mr
    0.57
    ⓧ
    0.57
    ruptedException
    0.57
    XmlAccessType
    0.57
    fohlen
    0.55
    Activations Density 0.204%

    No Known Activations