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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential actions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "can be" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    be found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.59
     solares
    -0.52
    msgSender
    -0.50
    WireFormat
    -0.50
    allow
    -0.49
     domestiques
    -0.49
    次第
    -0.47
    tionary
    -0.47
    ortable
    -0.47
    rungsseite
    -0.46
    POSITIVE LOGITS
     found
    0.89
     seen
    0.85
    found
    0.75
     downloaded
    0.73
     glimp
    0.72
     traced
    0.71
     accessed
    0.71
     viewed
    0.70
     dilihat
    0.69
    """.
    0.68
    Activations Density 0.254%

    No Known Activations