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. 7-GEMMASCOPE-RES-16K
    6. 9354
    Prev
    Next
    INDEX
    Explanations

    terms related to Android layout components and implementation details

    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
    DeleteBehavior
    -0.54
    لوم
    -0.53
    FXML
    -0.53
    SqlClient
    -0.52
     uintptr
    -0.48
    CHELL
    -0.48
    leukin
    -0.47
     ох
    -0.47
     Eche
    -0.46
    </i>
    -0.46
    POSITIVE LOGITS
    AccessorTable
    1.21
     CreateTagHelper
    0.86
    addCriterion
    0.85
    BufferException
    0.81
    matchCondition
    0.80
    WriteBarrier
    0.75
     onCancelled
    0.75
    Carriera
    0.74
    LayoutInflater
    0.74
     AssemblyProduct
    0.72
    Activations Density 0.005%

    No Known Activations