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. 2853
    Prev
    Next
    INDEX
    Explanations

    instances of object creation in programming code

    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
     виправивши
    -0.93
     Meksiku
    -0.88
     EconPapers
    -0.79
    expandindo
    -0.78
     Италијани
    -0.77
    HSSF
    -0.75
    Atsauces
    -0.73
    :✨
    -0.72
    ]")]
    -0.72
     Shakspeare
    -0.71
    POSITIVE LOGITS
    .
    0.49
    med
    0.49
    </td>
    0.48
    <unused63>
    0.45
    sed
    0.44
    よう
    0.44
    mer
    0.43
     brû
    0.43
    âme
    0.42
     father
    0.42
    Activations Density 0.034%

    No Known Activations