© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 16157
    Prev
    Next
    INDEX
    Explanations

    phrases related to healing, resolution, and managing debts or finances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    లాలు
    -0.58
     rarement
    -0.55
     muito
    -0.54
     GenerationType
    -0.52
     rarely
    -0.51
     rất
    -0.48
     muy
    -0.47
    fieldLabel
    -0.46
     sangat
    -0.46
    以上です
    -0.44
    POSITIVE LOGITS
     properly
    1.51
     safely
    1.30
    properly
    1.30
     efficiently
    1.21
     Properly
    1.17
     adequately
    1.16
     correctly
    1.12
     successfully
    1.08
     convenable
    1.08
     correctement
    1.08
    Activations Density 0.532%

    No Known Activations