© 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. 18-GEMMASCOPE-RES-16K
    11. 339
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court procedures and rulings

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

    Section/code references with numbers

    np_acts-logits-general · gemini-2.0-flash

    statute section numbers

    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
    SourceChecksum
    -0.83
    bootstrapcdn
    -0.74
    {#
    -0.60
    cshtml
    -0.59
     AssemblyCulture
    -0.58
     IBOutlet
    -0.57
    encodeWith
    -0.56
    endphp
    -0.56
    Gön
    -0.56
    djangoproject
    -0.56
    POSITIVE LOGITS
     (§
    0.64
    ::::::::
    0.57
     passim
    0.49
     statutes
    0.47
     Kensington
    0.45
     censiti
    0.44
    visor
    0.44
    przed
    0.43
     perle
    0.43
     hedgehog
    0.43
    Activations Density 0.408%

    No Known Activations