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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14330
    Prev
    Next
    INDEX
    Explanations

    expressions related to data handling and processing protocols

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

    after punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    verbs indicating completion

    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
     EconPapers
    -0.96
    elemField
    -0.85
    Bringing
    -0.82
     furnish
    -0.78
     Bringing
    -0.77
     Providing
    -0.76
     uncover
    -0.76
     Becoming
    -0.76
    arrive
    -0.74
    achieve
    -0.73
    POSITIVE LOGITS
    ByType
    0.44
     Bande
    0.41
    LogFile
    0.39
    OrEmpty
    0.39
    SubMenu
    0.39
    hã
    0.37
    Case
    0.37
    AsString
    0.37
     Mud
    0.36
    Cell
    0.35
    Activations Density 0.546%

    No Known Activations