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. 9-GEMMASCOPE-RES-16K
    6. 1509
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or text, indicating the start of a significant section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    titleMargin
    -1.16
    featureID
    -1.07
    Personendaten
    -1.05
    webElementXpaths
    -1.04
    NameInMap
    -1.01
     Walkover
    -1.00
    parsedMessage
    -1.00
    ItemBackground
    -0.98
    Vidite
    -0.98
    kháu
    -0.98
    POSITIVE LOGITS
    гова
    0.43
    ↵
    0.42
    [toxicity=0]
    0.39
     Smyth
    0.39
    ↵↵
    0.37
    #
    0.37
    0.37
     Dan
    0.36
     he
    0.36
    人都
    0.36
    Activations Density 0.889%

    No Known Activations