© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 485
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and data structure management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enabling
    -0.57
    PasswordField
    -0.55
     courants
    -0.54
     enable
    -0.54
     enables
    -0.49
     către
    -0.49
    wä
    -0.47
     betweenstory
    -0.47
    Enable
    -0.45
     defending
    -0.45
    POSITIVE LOGITS
     виправивши
    0.95
    GroupLayout
    0.82
    TagMode
    0.80
     calendriers
    0.73
     BorderSide
    0.72
     consultato
    0.72
     NSCoder
    0.70
    SourceChecksum
    0.70
    Tikang
    0.68
    OrBuilder
    0.67
    Activations Density 2.179%

    No Known Activations