Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5125
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references, particularly those related to statutes and crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.58
    enumii
    -0.57
    "]]
    -0.55
    inander
    -0.49
     kasarigan
    -0.48
    водства
    -0.48
    COMING
    -0.47
     MERCHANTABILITY
    -0.46
    borns
    -0.45
     Coming
    -0.45
    POSITIVE LOGITS
     upon
    1.15
     auquel
    1.04
     UPON
    0.98
     waarop
    0.96
     auxquels
    0.96
     whence
    0.95
     auxquelles
    0.93
    upon
    0.92
     onto
    0.89
     duquel
    0.85
    Activations Density 0.587%

    No Known Activations