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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1393
    Prev
    Next
    INDEX
    Explanations

    legal terminologies and concepts related to trial and post-conviction processes

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

    Legal or court documents

    np_acts-logits-general · gemini-2.0-flash

    document structure and punctuation

    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
     насељу
    -0.70
    ngdoc
    -0.67
    antMatchers
    -0.66
     Beecher
    -0.61
    neté
    -0.61
     eccell
    -0.61
    OrNil
    -0.60
     Signalez
    -0.60
    TemporalType
    -0.59
    ſelf
    -0.59
    POSITIVE LOGITS
    ########.
    0.58
    <![
    0.52
    <blockquote>
    0.51
    MathML
    0.49
    殊
    0.48
    addGap
    0.48
     kaynağından
    0.47
    ALTH
    0.47
    <tr>
    0.47
     Schluss
    0.46
    Activations Density 0.157%

    No Known Activations