© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10385
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating certainty or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Diweddarwch
    -0.81
     للاسماء
    -0.78
     فريبيس
    -0.77
     Taktlose
    -0.71
     disambiguazione
    -0.70
    parsedMessage
    -0.69
     Normdatei
    -0.69
     AssemblyVersion
    -0.65
     صوتيه
    -0.63
    rrggbb
    -0.62
    POSITIVE LOGITS
     člověk
    0.47
     Autoren
    0.43
     Wikiseite
    0.43
    oare
    0.41
     mano
    0.40
     раз
    0.40
    倒
    0.40
    fail
    0.39
    在
    0.39
    bool
    0.39
    Activations Density 1.071%

    No Known Activations