© 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. 2-GEMMASCOPE-RES-16K
    11. 4378
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.42
    並ぶ
    -0.35
    IconModule
    -0.34
    違います
    -0.34
     lines
    -0.34
     услыша
    -0.33
    <!--[
    -0.33
    VersionUID
    -0.33
     honors
    -0.33
    が違う
    -0.32
    POSITIVE LOGITS
     puede
    2.11
     can
    2.05
     pueden
    1.99
     può
    1.93
     können
    1.93
     peuvent
    1.91
     dapat
    1.87
     pouvez
    1.86
     kann
    1.85
    puede
    1.84
    Activations Density 0.294%

    No Known Activations