© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104678
    Prev
    Next
    INDEX
    Explanations

    elements related to significant events or actions in a narrative context

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

    built, seen, her, guidelines

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    MemoryWarning
    -0.40
     iż
    -0.40
     ContentValues
    -0.40
     skall
    -0.39
     изпол
    -0.36
    niająca
    -0.35
     hubiese
    -0.34
     ulike
    -0.34
    Descarga
    -0.34
    mtrl
    -0.33
    POSITIVE LOGITS
     XNUMX
    0.82
     ​​
    0.65
    +#+
    0.60
    uxxxx
    0.59
    NUMX
    0.59
    NameInMap
    0.59
    ̵
    0.57
    __':
    
    0.54
    __":
    
    0.51
    reportWebVitals
    0.49
    Activations Density 0.003%

    No Known Activations