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. 22-GEMMASCOPE-RES-16K
    6. 12965
    Prev
    Next
    INDEX
    Explanations

    references to the month of May or related events

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

    "May" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    May followed by I or Day or v. or 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.74
    RegistryLite
    -0.72
    ModelAdmin
    -0.71
     <<<<<<<<<<<<<<
    -0.68
    RTEX
    -0.66
    IndentedString
    -0.65
    rungsseite
    -0.65
    DebuggerNonUser
    -0.63
    </tbody>
    -0.61
    __":
    
    -0.60
    POSITIVE LOGITS
    fair
    0.80
     mắn
    0.74
    flower
    0.74
    belline
    0.71
    day
    0.70
    May
    0.69
    onnaise
    0.65
     May
    0.62
     Day
    0.61
    Day
    0.61
    Activations Density 0.035%

    No Known Activations