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. 18-GEMMASCOPE-RES-16K
    6. 3205
    Prev
    Next
    INDEX
    Explanations

    phrases and words that denote methods, approaches, or ways of doing something efficiently

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

    "way to" or "ways to"

    np_acts-logits-general · gemini-2.0-flash

    way to do

    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
     insuffisamment
    -0.80
    CodeDom
    -0.72
    IsPostBack
    -0.72
     समीक्षाएं
    -0.71
     saites
    -0.66
     елның
    -0.66
    ScopeManager
    -0.64
    cokinetic
    -0.64
     Wiktionnaire
    -0.63
     MainAxisSize
    -0.62
    POSITIVE LOGITS
     to
    1.08
     for
    1.02
     để
    0.77
     לעשות
    0.69
     untuk
    0.69
     чтобы
    0.61
     utk
    0.55
     для
    0.55
     برای
    0.54
     upang
    0.52
    Activations Density 0.364%

    No Known Activations