© 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. 6527
    Prev
    Next
    INDEX
    Explanations

    terms related to document formatting and graphics programming

    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
    BufferException
    -0.93
     Shakspeare
    -0.82
     LoggerFactory
    -0.81
    UrlResolution
    -0.74
     quæ
    -0.71
    InputTagHelper
    -0.69
     Monfieur
    -0.69
    nourriture
    -0.66
     myſelf
    -0.65
     Efq
    -0.64
    POSITIVE LOGITS
    CloseOperation
    0.95
    NameInMap
    0.84
     cref
    0.83
    omitempty
    0.71
    帖最后由
    0.69
    cshtml
    0.69
     EconPapers
    0.68
    unfinished
    0.65
    WithIOException
    0.61
    HasAnnotation
    0.60
    Activations Density 0.004%

    No Known Activations