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. 24-GEMMASCOPE-RES-16K
    6. 4292
    Prev
    Next
    INDEX
    Explanations

    references to academic articles and documents, particularly in a digital object identifier (DOI) format and related URLs

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

    URLs or references to external resources

    np_acts-logits-general · gemini-2.0-flash

    URLs and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.48
    zeera
    -0.48
    +#+#
    -0.47
    翌
    -0.45
    bollah
    -0.45
    bufio
    -0.43
    ++.
    -0.43
    SequentialGroup
    -0.43
    StackNavigator
    -0.43
    ၅
    -0.43
    POSITIVE LOGITS
    Geplaatst
    0.67
    verifyException
    0.64
    Datuak
    0.62
    قایناق‌لار
    0.61
    parsedMessage
    0.60
    httphttps
    0.58
    enumii
    0.57
     Seeder
    0.57
     يتيمه
    0.56
    <?
    0.55
    Activations Density 0.561%

    No Known Activations