© 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. 18-GEMMASCOPE-RES-16K
    11. 2986
    Prev
    Next
    INDEX
    Explanations

    statistical analysis methods and terminology

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

    Statistical data analysis techniques (regression, PCA)

    np_acts-logits-general · gemini-2.0-flash

    regression analysis techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">/
    -0.53
    들은
    -0.50
    ansons
    -0.50
    inescent
    -0.50
    хь
    -0.49
    '>";
    -0.49
    PERATURE
    -0.49
     Ka
    -0.49
    दै
    -0.48
     numerus
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    1.02
     technique
    0.85
    InputBorder
    0.81
    WithIOException
    0.73
    CppMethod
    0.70
     procedure
    0.69
     techniques
    0.68
    technique
    0.68
     aplicado
    0.67
     Technique
    0.67
    Activations Density 1.409%

    No Known Activations