© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5391
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peggio
    -0.44
     corretamente
    -0.44
    iedenen
    -0.43
     Aseg
    -0.42
     régulier
    -0.41
     Wikiseite
    -0.40
     silenzio
    -0.40
    뀔
    -0.40
     roupa
    -0.40
     autrement
    -0.40
    POSITIVE LOGITS
    Impacts
    0.76
     impacts
    0.74
     Impact
    0.74
     Impacts
    0.72
     IMPACT
    0.72
     impact
    0.69
    Impact
    0.69
    IMPACT
    0.66
     limited
    0.66
     propOrder
    0.63
    Activations Density 0.071%

    No Known Activations