© 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. 6-GEMMASCOPE-RES-16K
    11. 5111
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to various processes and actions in the context of scientific and technical descriptions

    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
    之
    -0.59
     expanded
    -0.59
    cination
    -0.58
    ation
    -0.58
    _
    -0.57
    ity
    -0.56
    ization
    -0.56
    ction
    -0.54
    mation
    -0.54
    gence
    -0.54
    POSITIVE LOGITS
    AsUp
    0.87
     piú
    0.87
    __':
    0.86
     myſelf
    0.80
     electing
    0.80
    cydow
    0.79
     ogrod
    0.79
    __":
    0.78
    VELOP
    0.78
    "]),
    0.77
    Activations Density 1.115%

    No Known Activations