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. 2-GEMMASCOPE-RES-16K
    6. 6508
    Prev
    Next
    INDEX
    Explanations

    references to specific characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.81
    IUrlHelper
    -0.81
    parsedMessage
    -0.75
    Географи
    -0.74
     BoxDecoration
    -0.73
     Southwestern
    -0.72
     CreateTagHelper
    -0.71
    Aholisi
    -0.70
    حياته
    -0.69
    ειτουργ
    -0.69
    POSITIVE LOGITS
     Hong
    0.55
     soul
    0.54
    Absor
    0.52
     poule
    0.49
    loride
    0.48
    нодоро
    0.47
    après
    0.46
     courbe
    0.46
    Hong
    0.46
     kond
    0.45
    Activations Density 0.037%

    No Known Activations