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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15490
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate calculations or logical deductions

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

    Sentences starting with "If we"

    np_acts-logits-general · gemini-2.0-flash

    if we

    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
     nahilalakip
    -1.08
     lenker
    -1.02
    expandindo
    -0.93
    rrggbb
    -0.86
    脚注の使い方
    -0.86
     AssemblyTitle
    -0.85
    الحياه
    -0.85
    msgTypes
    -0.85
     Numerade
    -0.84
    featureID
    -0.81
    POSITIVE LOGITS
     comparing
    0.50
    Looking
    0.50
     from
    0.50
     Looking
    0.50
     compare
    0.50
     looking
    0.48
    greenrobot
    0.45
     xét
    0.45
    从
    0.44
     From
    0.44
    Activations Density 0.473%

    No Known Activations