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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14847
    Prev
    Next
    INDEX
    Explanations

    terms and references related to genetic testing and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.59
    titleMargin
    -0.54
     '\\;'
    -0.51
     ویکی‌پدی
    -0.50
     collage
    -0.48
    amental
    -0.48
    styleType
    -0.48
    astia
    -0.48
    itados
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.44
    ManagedBean
    0.41
    şört
    0.40
     estekak
    0.38
    RenderAtEndOf
    0.36
     tercero
    0.32
     henvisninger
    0.31
    InjectMocks
    0.31
    مراجع
    0.31
     onAnimation
    0.30
    Activations Density 0.549%

    No Known Activations