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. 8-GEMMASCOPE-RES-16K
    6. 11181
    Prev
    Next
    INDEX
    Explanations

    phrases related to laser technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     connexes
    -0.61
    ConstraintMaker
    -0.60
    StatusBadRequest
    -0.59
    thenia
    -0.59
    iações
    -0.57
    mybatisplus
    -0.56
     Савезне
    -0.53
    addCriterion
    -0.52
    المكان
    -0.52
    ]--;
    -0.51
    POSITIVE LOGITS
    getDescriptor
    0.56
     ProtoMessage
    0.52
    τως
    0.50
    RTEX
    0.47
    ooga
    0.47
    contentPane
    0.47
    TagMode
    0.47
     متعلقه
    0.47
    combo
    0.45
    atillo
    0.45
    Activations Density 0.560%

    No Known Activations