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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 13286
    Prev
    Next
    INDEX
    Explanations

    expressions of support and care within interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deja
    -0.42
     вме
    -0.40
     reports
    -0.39
     largo
    -0.37
     agreg
    -0.37
    Slf
    -0.36
    Sprintf
    -0.36
    amp
    -0.36
     implica
    -0.36
    baguna
    -0.35
    POSITIVE LOGITS
    featureID
    0.77
    onOptions
    0.74
    AsUp
    0.71
    GOTREF
    0.68
     bisogno
    0.67
     /\.(
    0.67
    enumii
    0.67
     struggling
    0.65
     difficultés
    0.65
     needy
    0.64
    Activations Density 0.354%

    No Known Activations