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. 16-GEMMASCOPE-RES-16K
    6. 14921
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of a need or requirement for improvement or innovation in a specific field or context

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

    Need or existence of something

    np_acts-logits-general · gemini-2.0-flash

    need for something missing

    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
    tonsoft
    -0.47
    本番
    -0.46
    сква
    -0.44
    getSystemService
    -0.44
    RunAsync
    -0.43
    AutoModerator
    -0.42
     متعلقه
    -0.42
    willReturn
    -0.42
    fass
    -0.42
     baratos
    -0.42
    POSITIVE LOGITS
     unmet
    0.97
     Existing
    0.87
     existing
    0.86
    KommentareTeilen
    0.85
     underserved
    0.82
    Existing
    0.82
     niche
    0.80
     dearth
    0.79
     Bedarf
    0.78
    existing
    0.78
    Activations Density 0.459%

    No Known Activations