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. 8-GEMMASCOPE-RES-16K
    6. 2017
    Prev
    Next
    INDEX
    Explanations

    URLs and HTML structure elements, particularly those associated with resource loading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ddots
    -0.58
     nargin
    -0.57
    nasse
    -0.55
    maketitle
    -0.54
     fortsetter
    -0.54
     >",
    -0.54
    SuppressMessage
    -0.53
     vario
    -0.53
     gostar
    -0.53
    ired
    -0.52
    POSITIVE LOGITS
     StatelessWidget
    0.80
     CreateTagHelper
    0.80
    PreferredItem
    0.68
    ReusableCell
    0.67
    makeText
    0.65
    googleapis
    0.65
     Wikimedijinoj
    0.64
    ctools
    0.64
     autorytatywna
    0.63
    zzleHttp
    0.63
    Activations Density 0.002%

    No Known Activations