© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4714
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal terms and proceedings

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

    that end in certain suffixes

    np_acts-logits-general · gemini-2.0-flash

    completing known prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ena
    -0.41
    ane
    -0.40
    ida
    -0.38
    ick
    -0.37
    chery
    -0.36
    inas
    -0.36
    cken
    -0.36
     nakalista
    -0.36
    kian
    -0.36
    ys
    -0.36
    POSITIVE LOGITS
     början
    0.34
    berdayakan
    0.33
     stället
    0.32
     igång
    0.30
    harapkan
    0.30
     före
    0.30
     vocales
    0.29
     felicitación
    0.29
    excess
    0.29
     fuerzas
    0.29
    Activations Density 2.636%

    No Known Activations