© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5181
    Prev
    Next
    INDEX
    Explanations

    terms related to therapy and family counseling, particularly focusing on mental health issues and familial relationships

    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
    closePath
    -0.62
    usstsein
    -0.57
     aprire
    -0.55
     subconscious
    -0.54
     laziness
    -0.54
     consciência
    -0.54
    writerow
    -0.53
     Leidenschaft
    -0.52
    äste
    -0.52
    squareup
    -0.50
    POSITIVE LOGITS
     coping
    0.65
     normative
    0.60
     للاسماء
    0.59
     erlebt
    0.57
    Atsauces
    0.56
     contextos
    0.55
     contexts
    0.54
     desist
    0.54
     vécu
    0.54
     risorse
    0.53
    Activations Density 0.861%

    No Known Activations