© 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. 8581
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of transferring information or items

    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
    ✨:
    -0.92
    mybatisplus
    -0.76
    }{||
    -0.71
     Keene
    -0.71
    judge
    -0.70
    setPointSize
    -0.70
    yszer
    -0.70
    sizeCache
    -0.69
    Punkt
    -0.69
    Oke
    -0.68
    POSITIVE LOGITS
     transfers
    1.95
     transfer
    1.86
     TRANSFER
    1.79
     Transfers
    1.76
    Transfer
    1.75
     Transfer
    1.75
    Transfers
    1.70
     transferred
    1.66
    transfer
    1.64
    TRANSFER
    1.59
    Activations Density 0.063%

    No Known Activations