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. 13159
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations and mathematical expressions

    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
     pubblico
    -0.51
     للاسماء
    -0.51
    less
    -0.48
    DataMember
    -0.47
     impossível
    -0.47
    Hochspringen
    -0.47
     persoane
    -0.46
    ViewFeatures
    -0.45
     boneless
    -0.45
     from
    -0.45
    POSITIVE LOGITS
     FetchType
    0.75
    ⁢
    0.74
    MigrationBuilder
    0.74
    ")){
    
    0.69
     MILL
    0.65
    "]);
    
    0.64
    dataclass
    0.64
     Multiplication
    0.62
    :+:
    0.62
     الدولى
    0.62
    Activations Density 0.883%

    No Known Activations