© 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. 11273
    Prev
    Next
    INDEX
    Explanations

    concepts related to belief systems and community values

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

    Prepositions followed by articles or other words

    np_acts-logits-general · gemini-2.0-flash

    of words and language

    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
     quizá
    -0.48
     urma
    -0.35
     resulta
    -0.34
     talvez
    -0.34
     probablemente
    -0.33
    ChromeDriver
    -0.32
     Herrn
    -0.32
    卻
    -0.31
    enumi
    -0.30
     mej
    -0.30
    POSITIVE LOGITS
    extAlignment
    0.76
     InputDecoration
    0.63
    verwijspagina
    0.62
    ValueStyle
    0.62
     kasarigan
    0.59
     Италијани
    0.57
     мәкал
    0.56
    AxisAlignment
    0.55
    OGND
    0.55
    xase
    0.53
    Activations Density 0.268%

    No Known Activations