© 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. 6506
    Prev
    Next
    INDEX
    Explanations

    references to attachments or attached files in documents

    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
    MemoryWarning
    -0.80
    rocco
    -0.76
    awtextra
    -0.75
    getColumnIndex
    -0.73
    addGap
    -0.72
     colspan
    -0.72
     GenerationType
    -0.70
    Rama
    -0.66
     alman
    -0.65
     שוליים
    -0.64
    POSITIVE LOGITS
     ATTACH
    1.58
     Attach
    1.56
     attachment
    1.52
     attachments
    1.49
     Attachment
    1.47
     attached
    1.46
     attaches
    1.46
    attach
    1.45
     attach
    1.44
     Attached
    1.42
    Activations Density 0.079%

    No Known Activations