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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 6364
    Prev
    Next
    INDEX
    Explanations

    punctuations and structural elements in a document

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

    Follows punctuation and precedes action verbs

    np_acts-logits-general · gemini-2.0-flash

    read, learn, click, check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    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
    -0.67
    InjectMocks
    -0.54
    TableField
    -0.53
    setVerticalGroup
    -0.53
    THISDAY
    -0.52
     pulumi
    -0.51
    URLException
    -0.50
    XMLSchema
    -0.49
    AndFlush
    -0.48
    featureID
    -0.47
    POSITIVE LOGITS
     Read
    1.81
     Learn
    1.74
     read
    1.73
    Learn
    1.60
     learn
    1.59
     Click
    1.55
     Check
    1.51
    Read
    1.46
     check
    1.42
     click
    1.40
    Activations Density 0.324%

    No Known Activations