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. 12-GEMMASCOPE-RES-16K
    6. 6122
    Prev
    Next
    INDEX
    Explanations

    sequences of conjunctions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.82
     termica
    -0.72
     centralization
    -0.71
     mínimos
    -0.68
     aDecoder
    -0.68
    inheritDoc
    -0.67
     IBOutlet
    -0.65
     ModelExpression
    -0.64
    rungsseite
    -0.63
     anonymity
    -0.63
    POSITIVE LOGITS
     very
    0.72
    且
    0.68
     highly
    0.67
     self
    0.63
     powerful
    0.61
    PreferredItem
    0.57
    IsPostBack
    0.56
     clear
    0.56
     well
    0.55
     extremely
    0.55
    Activations Density 0.272%

    No Known Activations