© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11431
    Prev
    Next
    INDEX
    Explanations

    elements related to modal verbs and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.46
    migrationBuilder
    -0.45
     GenerationType
    -0.44
    ValueGenerated
    -0.43
     ikkje
    -0.42
    tagHelperRunner
    -0.41
     Dicapai
    -0.41
     majd
    -0.40
    ⓘ
    -0.40
     briefly
    -0.40
    POSITIVE LOGITS
     does
    0.45
    เอง
    0.43
    Jumlah
    0.41
     Tatsache
    0.40
     shall
    0.40
     cavalli
    0.40
    Needless
    0.39
     hå
    0.39
     wied
    0.39
    Does
    0.38
    Activations Density 0.047%

    No Known Activations