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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2202
    Prev
    Next
    INDEX
    Explanations

    terms related to personal injury law and legal services in Maryland

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

    Follows prepositions, conjunctions, or possessive "'s"

    np_acts-logits-general · gemini-2.0-flash

    legal advice and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     OFDb
    -0.61
     रेटिंग
    -0.55
    styleType
    -0.55
     发表于
    -0.54
    +:+
    -0.53
     lloc
    -0.52
    AnchorStyles
    -0.52
    ConstraintMaker
    -0.52
     виправивши
    -0.50
     kasarigan
    -0.49
    POSITIVE LOGITS
     compassionate
    0.69
     noastre
    0.66
    Compassion
    0.66
     ſtate
    0.61
    ométrique
    0.59
     Compassion
    0.59
     poffe
    0.57
    FIGHT
    0.57
     iſt
    0.57
     poffible
    0.57
    Activations Density 0.133%

    No Known Activations