Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 8722
    Prev
    Next
    INDEX
    Explanations

    numerical data related to financial, health, or performance metrics

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

    Years or date ranges

    np_acts-logits-general · gemini-2.0-flash

    hyphens between years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.88
    MessageTagHelper
    -0.87
    contentLoaded
    -0.80
     Lightboxes
    -0.78
    Билгалдахарш
    -0.77
    verwijspagina
    -0.77
    AnchorStyles
    -0.77
     InputDecoration
    -0.75
     continúas
    -0.73
    JNIEnv
    -0.72
    POSITIVE LOGITS
     year
    0.47
     season
    0.46
    Viitteet
    0.45
     Verhältnisse
    0.42
     began
    0.41
     Vic
    0.40
     retenir
    0.40
     lalu
    0.40
    ש
    0.39
    erc
    0.39
    Activations Density 0.068%

    No Known Activations