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. 6-GEMMASCOPE-RES-16K
    6. 7030
    Prev
    Next
    INDEX
    Explanations

    phrases related to making gifts or offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    labelledby
    -0.54
     carrying
    -0.42
     volto
    -0.41
    CLR
    -0.41
     established
    -0.41
     arac
    -0.41
    muş
    -0.40
    ثيق
    -0.40
    igte
    -0.40
     сор
    -0.40
    POSITIVE LOGITS
    TagMode
    0.90
     تضيفلها
    0.85
     виправивши
    0.84
     utafitiHapana
    0.82
    AnchorStyles
    0.78
    ⓧ
    0.71
     excellent
    0.69
    excellent
    0.68
    Хоро
    0.66
     chi̍t
    0.66
    Activations Density 0.214%

    No Known Activations