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. 14136
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or strong emotional reactions

    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
    "]}
    -0.58
     πάντα
    -0.55
    mpt
    -0.54
     ipc
    -0.53
    Дереккөздер
    -0.52
    ultura
    -0.51
    IPC
    -0.51
     ")[
    -0.51
     ')[
    -0.51
    ;}
    -0.51
    POSITIVE LOGITS
    Whoa
    0.79
    ValueStyle
    0.74
     Whoa
    0.69
     yeah
    0.67
    rungsseite
    0.64
    SourceChecksum
    0.64
    uh
    0.64
     wow
    0.63
    CompleteListener
    0.63
    wow
    0.62
    Activations Density 0.070%

    No Known Activations