© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15340
    Prev
    Next
    INDEX
    Explanations

    data structures and relationships in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecap
    -0.58
     repur
    -0.44
    messageInfo
    -0.42
     ويكيپيديا
    -0.41
     cape
    -0.41
    xnn
    -0.40
    TProtocol
    -0.40
     tấm
    -0.40
     bagno
    -0.39
    arden
    -0.39
    POSITIVE LOGITS
     subtree
    1.39
     tree
    1.32
     parent
    1.24
     recursively
    1.21
     Tree
    1.21
    Tree
    1.20
     children
    1.19
     TREE
    1.17
     hierarchy
    1.13
    tree
    1.13
    Activations Density 0.836%

    No Known Activations