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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    function definitions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens after "public" or "[" in code

    np_acts-logits-general · gemini-2.0-flash

    public function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.87
     дописавши
    -0.78
    Хьажоргаш
    -0.65
    +#+#
    -0.64
    enumi
    -0.63
    uxxxx
    -0.60
     invokingState
    -0.60
     pinulongan
    -0.59
    хьтан
    -0.59
    EDEFAULT
    -0.59
    POSITIVE LOGITS
    ParallelGroup
    0.69
     defaultstate
    0.67
    IActionResult
    0.47
    voort
    0.47
     subdivision
    0.47
    Vorlage
    0.47
    esterday
    0.47
     MonoBehaviour
    0.47
    tagHelper
    0.46
    ⓧ
    0.46
    Activations Density 0.021%

    No Known Activations