© 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. 16-GEMMASCOPE-RES-16K
    11. 6850
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and the conditions under which remedies or appeals are granted in court cases

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

    infrequent actions

    np_acts-logits-general · gemini-2.0-flash

    conditions and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.81
     OFDb
    -0.67
     estekak
    -0.64
    __(/*!
    -0.63
     Biôgrafia
    -0.58
    Pranala
    -0.56
     समीक्षाओं
    -0.55
    FIG
    -0.54
    Datuak
    -0.53
    Enllaces
    -0.53
    POSITIVE LOGITS
     sparingly
    1.11
     rarely
    1.08
     seldom
    0.99
     infrequently
    0.97
    除非
    0.96
     unless
    0.93
     Rarely
    0.91
     only
    0.88
     rare
    0.87
    Unless
    0.85
    Activations Density 0.492%

    No Known Activations