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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3739
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to rights and judicial processes

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

    Values ending in ".5"

    np_acts-logits-general · gemini-2.0-flash

    cruel, liberty, substantive due process

    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
     adipis
    -0.48
    ratore
    -0.46
    帖最后由
    -0.45
     největ
    -0.41
    зка
    -0.39
    vdots
    -0.38
     apla
    -0.38
     presid
    -0.38
    cshtml
    -0.38
    Statics
    -0.37
    POSITIVE LOGITS
    ThroughAttribute
    0.97
    ]--;
    0.76
    addContainerGap
    0.73
    بوابة
    0.73
    CompilerServices
    0.72
    Rohy
    0.69
     AssemblyCulture
    0.67
     Exacts
    0.66
    addPreferredGap
    0.66
     Мексичка
    0.65
    Activations Density 0.257%

    No Known Activations