© 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. 11-GEMMASCOPE-RES-16K
    11. 7086
    Prev
    Next
    INDEX
    Explanations

    non-standard usage or modifications to established practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.88
     snippetHide
    -0.70
     Signalez
    -0.69
     Réponses
    -0.68
     InputDecoration
    -0.68
    parsedMessage
    -0.68
     ब्रेकडाउन
    -0.67
    +#+#
    -0.64
    WriteTagHelper
    -0.64
    MemoryWarning
    -0.62
    POSITIVE LOGITS
    ftagPool
    0.67
    ніципалі
    0.54
     Condensed
    0.49
     Kamer
    0.45
    "}";
    0.43
    cular
    0.42
    σθαι
    0.41
     BioLib
    0.41
     Creature
    0.39
     DEPOS
    0.39
    Activations Density 1.244%

    No Known Activations