Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 1109
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific acronyms related to scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.80
    tableFuture
    -0.70
    JspWriter
    -0.68
     Audiodateien
    -0.67
    المناصب
    -0.64
     téléph
    -0.64
    SharedDtor
    -0.64
    avigation
    -0.63
    erevan
    -0.61
    indak
    -0.61
    POSITIVE LOGITS
    DS
    1.05
    GS
    1.01
     ds
    1.00
    AMS
    0.97
    MS
    0.96
    IMS
    0.96
    ds
    0.95
     DS
    0.94
    KS
    0.94
    QS
    0.93
    Activations Density 3.401%

    No Known Activations