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. 18-GEMMASCOPE-RES-16K
    6. 14514
    Prev
    Next
    INDEX
    Explanations

    keywords related to asynchronous programming

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

    Code snippets using `await`

    np_acts-logits-general · gemini-2.0-flash

    await operations on state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.60
    IVEREF
    -0.58
    BagLayout
    -0.56
    </i>
    -0.56
     trás
    -0.54
    </b>
    -0.54
    ca
    -0.52
     Sarg
    -0.50
    cline
    -0.49
     takeaway
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.78
    arakhand
    0.78
    tagHelperRunner
    0.72
    odils
    0.69
     aimez
    0.67
     CreateTagHelper
    0.66
    anthin
    0.65
     suivants
    0.64
    pertory
    0.63
    __(/*!
    0.63
    Activations Density 0.026%

    No Known Activations