Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 8428
    Prev
    Next
    INDEX
    Explanations

    the presence of the article "a" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quedado
    -0.53
    mêmes
    -0.49
    Gemeinden
    -0.48
    Vezi
    -0.47
    sellors
    -0.46
    eraard
    -0.46
    lorum
    -0.45
    obacz
    -0.45
     للاسماء
    -0.44
     volna
    -0.44
    POSITIVE LOGITS
     they
    0.88
    twimg
    0.74
    oredCriteria
    0.67
    +:+
    0.67
    GeneratedValue
    0.65
    AutoresizingMask
    0.64
    BagLayout
    0.63
    ControllerAdvice
    0.63
    AnimationsModule
    0.63
     noqa
    0.63
    Activations Density 0.937%

    No Known Activations