© 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. 7056
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing clarity and simplification in explanations

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

    "For" followed by a reason or purpose

    np_acts-logits-general · gemini-2.0-flash

    for reasons or purposes

    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
    šinou
    -0.65
     addirittura
    -0.61
     HasFactory
    -0.61
     مشين
    -0.58
    windowFixed
    -0.56
     zelfs
    -0.54
     pourtant
    -0.53
    witness
    -0.53
     GenerationType
    -0.53
    principalColumn
    -0.52
    POSITIVE LOGITS
     simplicity
    1.46
     clarity
    1.12
     convenience
    1.09
     brevity
    1.08
     sake
    1.06
     purposes
    1.03
     ease
    1.00
     completeness
    0.97
     simplify
    0.86
     consistency
    0.84
    Activations Density 0.515%

    No Known Activations