Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 7058
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numbers
    -0.51
     numbers
    -0.51
    Numbers
    -0.48
    </h3>
    -0.45
    +:+
    -0.45
     NUMBERS
    -0.44
    収
    -0.43
     فض
    -0.43
     anul
    -0.42
    Substring
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.88
    ंदीखरीदारी
    0.85
     Walkover
    0.83
    LookAnd
    0.79
    ніципа
    0.79
     disambiguazione
    0.78
    ьаж
    0.78
    ftagPool
    0.77
    المناصب
    0.76
     propOrder
    0.76
    Activations Density 0.108%

    No Known Activations