Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15656
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial transactions and creditworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    covid
    -0.63
     ("
    -0.62
     मैंने
    -0.60
     utk
    -0.60
    ($"
    -0.59
     ggf
    -0.59
     &
    -0.59
    localctx
    -0.58
    adaptiveStyles
    -0.57
     vedo
    -0.57
    POSITIVE LOGITS
     $_"
    0.76
     convenable
    0.73
     ")");
    0.69
     beziehungs
    0.68
     MonoBehaviour
    0.67
    etheless
    0.64
     ?
    0.64
    ')));
    0.64
     StatefulWidget
    0.63
    Spoljašnje
    0.63
    Activations Density 0.365%

    No Known Activations