© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4050
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to processes and steps in scientific procedures

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

    following "to" indicating a purpose

    np_acts-logits-general · gemini-2.0-flash

    to ensure or promote an outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    __':
    
    -0.56
    __":
    -0.46
    __':
    -0.45
    __":
    
    -0.44
    jfree
    -0.43
    ostante
    -0.39
    balleur
    -0.39
     graphiques
    -0.39
     parlement
    -0.39
    cemment
    -0.39
    POSITIVE LOGITS
     ensures
    0.47
     للاسماء
    0.43
     helps
    0.43
     виправивши
    0.43
     allows
    0.42
     cassa
    0.41
     creates
    0.39
    writeFieldEnd
    0.39
     prevents
    0.38
     makes
    0.38
    Activations Density 0.757%

    No Known Activations