© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16039
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes or variations in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 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
    ValueGenerated
    -0.57
     chi̍t
    -0.53
    ➩
    -0.49
    لينكات
    -0.49
    ApplicationTests
    -0.49
    ViewImports
    -0.49
     tartalomajánló
    -0.46
    UnknownFieldSet
    -0.44
    gründung
    -0.43
    MessageTagHelper
    -0.42
    POSITIVE LOGITS
     iprot
    0.42
    writerow
    0.39
     изменение
    0.39
     superiori
    0.38
     aumentare
    0.38
    Changing
    0.37
    期刊论文
    0.37
    oglobulin
    0.36
     Weise
    0.36
     SEÑ
    0.36
    Activations Density 0.487%

    No Known Activations