© 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. 20-GEMMASCOPE-RES-16K
    11. 10636
    Prev
    Next
    INDEX
    Explanations

    references to comparative phrases indicating inclusion or similarity within groups

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

    "among"

    np_acts-logits-general · gemini-2.0-flash

    among others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LoginPage
    -0.54
     javafx
    -0.47
    LoginPage
    -0.46
    Ál
    -0.44
    liquid
    -0.44
     puls
    -0.43
    Morte
    -0.43
    DueDate
    -0.43
    Liefs
    -0.43
    scen
    -0.43
    POSITIVE LOGITS
     among
    1.23
    among
    1.12
     AMONG
    1.08
    Among
    1.05
     Among
    1.05
     parmi
    0.97
     amongst
    0.96
     Amongst
    0.85
     wśród
    0.84
    Среди
    0.82
    Activations Density 0.080%

    No Known Activations