© 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. 38-GEMMASCOPE-RES-16K
    6. 9508
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.73
     <<<<<<<<<<<<<<
    -0.62
     Италијани
    -0.60
     Numerade
    -0.59
    pexpr
    -0.54
    Література
    -0.54
    ViewFeatures
    -0.53
    CodedInputStream
    -0.52
    AutoScaleMode
    -0.52
    SpringRunner
    -0.52
    POSITIVE LOGITS
     used
    2.92
    Used
    2.44
     Used
    2.41
    used
    2.36
     USED
    2.09
     usado
    1.84
     usados
    1.71
     accustomed
    1.70
     usadas
    1.66
     usada
    1.63
    Activations Density 0.265%

    No Known Activations