© 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. 15-GEMMASCOPE-RES-16K
    11. 5836
    Prev
    Next
    INDEX
    Explanations

    discussions around concepts of belief and accountability regarding interpersonal and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kalan
    -0.57
    nian
    -0.57
    بالإنجليزية
    -0.57
    onian
    -0.56
     the
    -0.56
    führen
    -0.54
    koda
    -0.53
    みると
    -0.53
    rian
    -0.53
    ftance
    -0.52
    POSITIVE LOGITS
     me
    0.97
    \{\\
    0.89
     him
    0.88
     us
    0.87
     you
    0.83
     ujednoznacz
    0.77
    enumi
    0.77
     saites
    0.72
    tagHelperRunner
    0.72
     them
    0.71
    Activations Density 0.330%

    No Known Activations