© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15331
    Prev
    Next
    INDEX
    Explanations

    mentions of personal ownership or individuality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Tracce
    -0.50
     réfrig
    -0.49
    sweise
    -0.46
    DbType
    -0.46
    racht
    -0.44
     vuotta
    -0.42
    Schriften
    -0.42
    了嗎
    -0.42
    úsica
    -0.41
    CURLOPT
    -0.40
    POSITIVE LOGITS
     own
    1.38
     Own
    1.10
    Own
    1.09
    own
    1.08
     OWN
    0.98
     eigene
    0.93
     egne
    0.93
     eigenen
    0.89
     włas
    0.88
     egna
    0.87
    Activations Density 0.035%

    No Known Activations