© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7535
    Prev
    Next
    INDEX
    Explanations

    the adverb "correctly" and its variations, indicating a focus on accuracy in processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.81
    StoryboardSegue
    -0.79
    GenerationType
    -0.72
    ~=
    -0.69
    providedIn
    -0.67
     AssemblyVersion
    -0.67
    BeginInit
    -0.66
     Nod
    -0.64
    XmlAccessorType
    -0.63
    utilisons
    -0.63
    POSITIVE LOGITS
     correctly
    1.03
     incorrectly
    0.72
    correctly
    0.69
     rightly
    0.68
     essentially
    0.64
     properly
    0.60
     eventually
    0.59
     preva
    0.58
    aziland
    0.57
     appropriately
    0.56
    Activations Density 0.068%

    No Known Activations