© 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. 2201
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts and procedural details in courtroom settings

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

    Preceding words of quantities or judgements

    np_acts-logits-general · gemini-2.0-flash

    lost profits, harmless error, large N

    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
     <<<<<<<<<<<<<<
    -0.59
    。
    -0.55
     the
    -0.53
    .]
    -0.52
    ].
    -0.52
    </h4>
    -0.47
     pregi
    -0.46
     convain
    -0.45
     .
    -0.45
    』。
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
     Мексичка
    0.93
    +#+#
    0.91
    webElementXpaths
    0.84
    setVerticalGroup
    0.83
    LookAnd
    0.79
     beginnetje
    0.78
    MigrationBuilder
    0.77
    SizeF
    0.72
    StoryboardSegue
    0.69
    Activations Density 0.860%

    No Known Activations