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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8634
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to sequences and functions

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

    Mathematical notation and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and context

    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
     first
    -0.89
    first
    -0.63
     FIRST
    -0.58
     firstly
    -0.57
     First
    -0.57
     primero
    -0.53
    First
    -0.53
    Firstly
    -0.53
     أول
    -0.52
     }}=\
    -0.52
    POSITIVE LOGITS
    PerformLayout
    0.73
    HasForeignKey
    0.72
     étoit
    0.69
     '\\;'
    0.68
     généraux
    0.67
     démocr
    0.66
     avoient
    0.65
     chrétiens
    0.64
    且
    0.64
     الرياضيه
    0.63
    Activations Density 1.616%

    No Known Activations