© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40-GEMMASCOPE-RES-16K
    11. 6985
    Prev
    Next
    INDEX
    Explanations

    terms indicating growth, increase, or escalation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increased
    -0.45
    increased
    -0.44
     constitutions
    -0.38
     increasing
    -0.37
    CreateModel
    -0.37
    principalColumn
    -0.36
     greateſt
    -0.36
    geschichte
    -0.35
    Increased
    -0.35
    <()>
    -0.35
    POSITIVE LOGITS
     chances
    0.91
     likelihood
    0.91
     awareness
    0.77
     number
    0.76
     frequency
    0.74
     reliance
    0.73
     popularity
    0.73
     jumlah
    0.72
     complexity
    0.71
     probability
    0.71
    Activations Density 0.646%

    No Known Activations