© 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. 9-GEMMASCOPE-RES-131K
    6. 45041
    Prev
    Next
    INDEX
    Explanations

    technical terms related to cryptography and electron beam technology

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

    electron beam lithography, confinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tân
    -0.34
    digen
    -0.34
     poverty
    -0.33
     DIY
    -0.33
     photo
    -0.32
    adox
    -0.32
    rants
    -0.31
     bolig
    -0.31
     paci
    -0.31
     positive
    -0.31
    POSITIVE LOGITS
    StructEnd
    0.69
    parsedMessage
    0.62
    RegressionTest
    0.61
    chartInstance
    0.57
     pinulongan
    0.57
    Vidite
    0.53
    irited
    0.52
    exitRule
    0.52
     kaynağından
    0.50
    Билгалдахарш
    0.50
    Activations Density 0.180%

    No Known Activations