© 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. 16-GEMMASCOPE-RES-16K
    11. 1081
    Prev
    Next
    INDEX
    Explanations

    numerical values and expressions

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

    Mathematical/chemical formulas and expressions

    np_acts-logits-general · gemini-2.0-flash

    numbers, abbreviations, or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.93
     surla
    -0.83
    Diweddarwch
    -0.82
    tagHelperRunner
    -0.81
    WithIOException
    -0.74
     AttributeSet
    -0.72
     дописавши
    -0.70
    ThroughAttribute
    -0.70
    TemporalType
    -0.68
     ResourceManager
    -0.67
    POSITIVE LOGITS
     etc
    0.58
     fhort
    0.54
     usw
    0.53
     infine
    0.51
     Majefty
    0.50
     itp
    0.50
    などなど
    0.49
     Jefus
    0.49
    最快更新
    0.47
    IntoConstraints
    0.47
    Activations Density 0.907%

    No Known Activations