© 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. 3-GEMMASCOPE-RES-16K
    11. 10411
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting elements in technical or scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.26
     utafitiHapana
    -1.02
     mergeFrom
    -0.98
    tvguidetime
    -0.97
     '\\;'
    -0.96
    AddTagHelper
    -0.95
    AccessorTable
    -0.93
     noDo
    -0.92
    AnchorStyles
    -0.92
    SequentialGroup
    -0.91
    POSITIVE LOGITS
     mostly
    0.52
     viață
    0.47
     justiça
    0.47
     generally
    0.46
     morire
    0.41
    こと
    0.41
     duração
    0.40
     Congrès
    0.40
    mostly
    0.40
     overall
    0.39
    Activations Density 0.538%

    No Known Activations