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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 12911
    Prev
    Next
    INDEX
    Explanations

    expressions of societal critique and commentary on contemporary issues related to culture and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.71
    IntoConstraints
    -0.68
     étoit
    -0.67
    InjectAttribute
    -0.64
     fevere
    -0.64
     neceff
    -0.63
     avoient
    -0.62
     houſe
    -0.60
     ſever
    -0.60
     avoit
    -0.60
    POSITIVE LOGITS
     increasingly
    0.67
    cheinend
    0.63
     MainAxisSize
    0.61
     zuneh
    0.56
     lack
    0.56
     trend
    0.55
     ormai
    0.53
    openzeppelin
    0.52
     America
    0.51
    最近の
    0.51
    Activations Density 0.445%

    No Known Activations