© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant number or frequency of instances and their implications in various contexts

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

    "Many" followed by what happens to something/someone

    np_acts-logits-general · gemini-2.0-flash

    quantified plural subjects

    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
    ionales
    -0.42
    WithIdentifier
    -0.41
     PARTIC
    -0.37
    SOUNDBITE
    -0.36
    wnia
    -0.36
    PathVariable
    -0.35
    hrer
    -0.35
    Vidite
    -0.35
    短短
    -0.35
    Autoritní
    -0.35
    POSITIVE LOGITS
     Muchos
    0.66
    Veel
    0.65
     flesta
    0.63
    Majority
    0.62
    Many
    0.61
     Beaucoup
    0.60
     Muitos
    0.60
     majority
    0.59
    Beaucoup
    0.59
    Viele
    0.58
    Activations Density 0.397%

    No Known Activations