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. 9-GEMMASCOPE-RES-16K
    6. 9146
    Prev
    Next
    INDEX
    Explanations

    specific elements related to identifiers and layout attributes in Android code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    स्व
    -0.46
    <eos>
    -0.45
    ništvo
    -0.44
    рс
    -0.43
    <0xEA>
    -0.41
     parti
    -0.41
    wür
    -0.41
     đ
    -0.40
    äjä
    -0.39
     espec
    -0.39
    POSITIVE LOGITS
     _('
    1.01
     '@/
    0.96
    enumi
    0.96
    ](#
    0.95
    ::_('
    0.93
     _("
    0.86
    脚注の使い方
    0.84
     "..\..\..\
    0.82
     ویکی‌پدیا
    0.82
     "@/
    0.81
    Activations Density 0.008%

    No Known Activations