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. 5315
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data processing and analysis

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

    following technical or specific terms

    np_acts-logits-general · gemini-2.0-flash

    calibration curve

    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
     للمعارف
    -0.68
    wain
    -0.68
    loroethene
    -0.60
    kuuta
    -0.58
    inthians
    -0.58
    حوالہ
    -0.57
    ″]
    -0.57
     ProtoMessage
    -0.56
     Wiktionnaire
    -0.56
    Atsauces
    -0.56
    POSITIVE LOGITS
     zone
    0.64
     points
    0.55
     mechanism
    0.55
     box
    0.54
     sheets
    0.54
     zones
    0.54
     clause
    0.54
     sheet
    0.53
     areas
    0.53
     berupa
    0.52
    Activations Density 1.497%

    No Known Activations