© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2895
    Prev
    Next
    INDEX
    Explanations

    legal terminology and procedural concepts related to appeals and court rulings

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

    preceding conditions ("unless," "if," "when")

    np_acts-logits-general · gemini-2.0-flash

    unless, where, if, or not

    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
    somewhat
    -0.61
     ganske
    -0.60
     somewhat
    -0.59
     almost
    -0.58
     entsprechend
    -0.58
     correspondingly
    -0.57
    almost
    -0.56
     suitably
    -0.56
     pretty
    -0.55
    wiście
    -0.53
    POSITIVE LOGITS
     unless
    1.63
    unless
    1.43
     unnecessarily
    1.37
     nor
    1.32
     anymore
    1.29
    Unless
    1.23
     Unless
    1.21
     needlessly
    1.15
     inneces
    1.07
     lest
    1.05
    Activations Density 0.460%

    No Known Activations