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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9284
    Prev
    Next
    INDEX
    Explanations

    references to prices and discounts in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parere
    -0.46
    IGENCE
    -0.45
    Aiheesta
    -0.44
    :+:
    -0.43
    Più
    -0.42
    PyObject
    -0.41
     Перейти
    -0.40
     trajet
    -0.39
     faudrait
    -0.39
    כח
    -0.39
    POSITIVE LOGITS
     ExecuteAsync
    0.82
    ंदीखरीदारी
    0.71
     NavController
    0.69
    ArgsConstructor
    0.68
    PropertyChanging
    0.68
    ]^{-
    0.65
    ]=>
    0.64
     jScrollPane
    0.64
    ValueGeneration
    0.64
     ProtoMessage
    0.61
    Activations Density 0.608%

    No Known Activations