Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3898
    Prev
    Next
    INDEX
    Explanations

    terms related to psychological concepts and distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.69
    ֹא
    -0.66
     Accesat
    -0.65
    HttpPut
    -0.64
    Extinguishing
    -0.64
    SourceChecksum
    -0.63
     kohdetta
    -0.62
    fromLTRB
    -0.62
    arrivée
    -0.61
     CONTENT
    -0.61
    POSITIVE LOGITS
     psychology
    1.80
     psychological
    1.80
     Psychological
    1.72
     PSYCH
    1.71
     psychologists
    1.67
     psychologist
    1.66
     Psychology
    1.64
    Psychological
    1.61
     Psycho
    1.59
    psychological
    1.57
    Activations Density 0.102%

    No Known Activations