Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 10055
    Prev
    Next
    INDEX
    Explanations

    mentions of authors, their works, or literary contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Obrázky
    -0.54
    фан
    -0.51
    icznie
    -0.46
     خام
    -0.45
    际
    -0.42
     BoxDecoration
    -0.42
    GLOBALS
    -0.41
    formazione
    -0.41
    Margot
    -0.41
     impianti
    -0.40
    POSITIVE LOGITS
    aarrggbb
    0.82
     extraordinaire
    0.81
     CreateTagHelper
    0.78
     betweenstory
    0.74
     Efq
    0.73
    :✨
    0.69
    ❋
    0.69
     initComponents
    0.65
    tagHelperRunner
    0.65
     racon
    0.65
    Activations Density 0.276%

    No Known Activations