© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11783
    Prev
    Next
    INDEX
    Explanations

    legal terminology relating to conditions under which actions and injuries are deemed valid or material in a legal context

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

    Preceding conditional words ("when", "if", etc.)

    np_acts-logits-general · gemini-2.0-flash

    precedes "if" or "when"

    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
    ReusableCell
    -0.76
    WaitGroup
    -0.69
     myſelf
    -0.68
    MigrationBuilder
    -0.64
     ſever
    -0.62
     Beſ
    -0.60
     purpoſe
    -0.60
     Theſe
    -0.60
     uſed
    -0.59
     Conſ
    -0.59
    POSITIVE LOGITS
     when
    1.36
     if
    1.15
     quando
    1.00
     cuando
    0.98
     lorsque
    0.94
    when
    0.90
     जब
    0.84
     lorsqu
    0.83
     wanneer
    0.81
     khi
    0.81
    Activations Density 0.672%

    No Known Activations