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. 14-GEMMASCOPE-RES-16K
    6. 10541
    Prev
    Next
    INDEX
    Explanations

    specific key attributes and characteristics of entities or concepts described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.58
     betweenstory
    -0.57
    CloseOperation
    -0.53
     Cek
    -0.53
     AssemblyTitle
    -0.52
    ClCompile
    -0.52
     pié
    -0.52
    RegressionTest
    -0.49
    protoimpl
    -0.49
     الاطلاع
    -0.49
    POSITIVE LOGITS
     itself
    0.77
    tagHelper
    0.69
    itself
    0.61
    seamnă
    0.59
     indeed
    0.57
     aceptas
    0.54
     cherchés
    0.52
     also
    0.52
    первых
    0.51
     officially
    0.49
    Activations Density 0.449%

    No Known Activations