© 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. 24-GEMMASCOPE-RES-16K
    11. 9362
    Prev
    Next
    INDEX
    Explanations

    structured code elements and class definitions in programming contexts

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

    Code snippets or programming-related keywords

    np_acts-logits-general · gemini-2.0-flash

    home / homepage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.56
    Abitanti
    -0.53
    ksom
    -0.50
     HasFactory
    -0.48
    DebuggerStep
    -0.47
    protoimpl
    -0.44
    field
    -0.43
     endregion
    -0.41
    disfraz
    -0.41
     dieną
    -0.39
    POSITIVE LOGITS
     home
    1.17
    Home
    1.15
     Home
    1.13
    home
    1.12
     homepage
    1.10
    HomePage
    1.07
     HomePage
    1.06
     HOME
    1.04
    welcome
    1.03
     Homepage
    1.02
    Activations Density 0.189%

    No Known Activations