© 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. 20-GEMMASCOPE-RES-16K
    11. 13060
    Prev
    Next
    INDEX
    Explanations

    statistical measures and comparisons related to concentrations and their effects

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

    Comparative adjectives following "is/was/are"

    np_acts-logits-general · gemini-2.0-flash

    states of comparison

    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
     lenker
    -0.63
     autorytatywna
    -0.61
    ########.
    -0.60
    AndEndTag
    -0.59
    UnsafeEnabled
    -0.59
     विश्वसनीयता
    -0.58
     gynhyrchwyd
    -0.56
    mybatisplus
    -0.56
     HasFactory
    -0.55
    DockStyle
    -0.54
    POSITIVE LOGITS
     higher
    0.99
     greater
    0.92
     larger
    0.87
     smaller
    0.85
    higher
    0.81
     bigger
    0.77
     equal
    0.75
     lower
    0.74
    larger
    0.71
    greater
    0.70
    Activations Density 0.992%

    No Known Activations