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. 19-GEMMASCOPE-RES-16K
    6. 15004
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in code, particularly dropdown menus and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.63
     وتسجيلات
    -0.60
    MemoryWarning
    -0.60
     peine
    -0.60
     BIBSYS
    -0.56
     referenties
    -0.54
    WebControls
    -0.51
     bArr
    -0.51
     peines
    -0.50
     vastaan
    -0.50
    POSITIVE LOGITS
     active
    0.93
    active
    0.91
    Active
    0.78
     selected
    0.77
    selected
    0.75
     attiva
    0.72
     aktif
    0.70
     Active
    0.70
     activo
    0.68
     ACTIVE
    0.66
    Activations Density 0.241%

    No Known Activations