© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16089
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" and its variations in different contexts

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

    Preceding "mere," "flash," "Ho," "world," "down," "menacing," or "post."

    np_acts-logits-general · gemini-2.0-flash

    "a" followed by common words

    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
    Становништво
    -0.54
    GOTREF
    -0.53
    ungsbedingungen
    -0.50
     pages
    -0.48
    Menus
    -0.46
     &___
    -0.46
     fondament
    -0.46
    ungen
    -0.45
     carico
    -0.45
    Demografie
    -0.45
    POSITIVE LOGITS
    sizeCache
    0.92
     hurry
    0.86
    lighet
    0.82
     nutshell
    0.76
    nuts
    0.73
    Datuak
    0.72
    rungsseite
    0.71
     bid
    0.66
     naselje
    0.65
    elemField
    0.62
    Activations Density 0.245%

    No Known Activations