© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12021
    Prev
    Next
    INDEX
    Explanations

    terms related to product returns and customer satisfaction policies

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

    returns and refunds

    np_acts-logits-general · gemini-2.0-flash

    refund or replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Референце
    -0.50
     uintptr
    -0.49
     ProtoMessage
    -0.45
     betweenstory
    -0.45
    providedIn
    -0.45
    moveToNext
    -0.42
     clearances
    -0.41
    ηγ
    -0.41
    digd
    -0.41
     endforeach
    -0.41
    POSITIVE LOGITS
     refund
    1.05
     refunds
    1.01
     Refund
    0.94
     refunded
    0.90
     REFUND
    0.90
     Refunds
    0.86
    Refunds
    0.83
    Refund
    0.80
    ViewFeatures
    0.79
     Customer
    0.78
    Activations Density 0.104%

    No Known Activations