© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10933
    Prev
    Next
    INDEX
    Explanations

    numeric values and their relationships within data structures

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

    The number 2

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.96
     ویکی‌پدی
    -0.78
    majánló
    -0.74
    pecabe
    -0.73
    تقاوى
    -0.71
    ikusbot
    -0.67
    CloseOperation
    -0.67
    ſſung
    -0.65
    ſchaft
    -0.65
     témoig
    -0.65
    POSITIVE LOGITS
    2
    1.34
    ２
    0.64
    3
    0.55
    4
    0.49
    ২
    0.49
    २
    0.47
    ۲
    0.47
    8
    0.46
    ²
    0.46
    ٢
    0.45
    Activations Density 1.072%

    No Known Activations