© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15925
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns, especially those that are repetitive or part of ongoing themes

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

    followed by "thy" or names ending in "ne"

    np_acts-logits-general · gemini-2.0-flash

    names like Rene and Arne

    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
    tas
    -0.55
    ا
    -0.52
    da
    -0.51
    dahl
    -0.50
    ضو
    -0.47
    т
    -0.47
    ะ
    -0.47
    té
    -0.46
    gate
    -0.46
    tal
    -0.46
    POSITIVE LOGITS
    nnn
    1.05
    nnnn
    1.04
     JNI
    0.94
     DNC
    0.91
    onedDateTime
    0.88
     Pn
    0.88
    XmlAccessorType
    0.87
     Dn
    0.87
    JNIEnv
    0.87
     GNP
    0.85
    Activations Density 0.589%

    No Known Activations