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. 11790
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in scientific research or studies

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

    Followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    looking for

    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
     sort
    -0.52
    ّد
    -0.50
    —
    -0.50
     —
    -0.48
     --
    -0.48
     situ
    -0.47
    ice
    -0.47
    devise
    -0.47
     the
    -0.46
    Po
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    0.76
     المعيارى
    0.76
    lossians
    0.74
     تانيه
    0.71
    __*/
    0.70
     تضيفلها
    0.67
     CreateTagHelper
    0.65
     kaynağından
    0.64
     Jop
    0.64
     שוליים
    0.63
    Activations Density 0.039%

    No Known Activations