© 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. 24-GEMMASCOPE-RES-16K
    11. 9741
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that indicate user requirements or inquiries

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

    "you" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    you want or need

    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
    triangleq
    -0.63
    CloseOperation
    -0.60
    tagHelper
    -0.50
    XMLSchema
    -0.50
     InputDecoration
    -0.50
    laughs
    -0.49
    ocrine
    -0.49
    IBinder
    -0.49
    PYX
    -0.48
    kranz
    -0.48
    POSITIVE LOGITS
     prefer
    0.84
     Prefer
    0.74
     want
    0.70
    prefer
    0.67
    มาะ
    0.66
     need
    0.65
     looking
    0.64
     fancy
    0.63
    Already
    0.63
     already
    0.61
    Activations Density 0.126%

    No Known Activations