© 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. 24-GEMMASCOPE-RES-16K
    11. 5179
    Prev
    Next
    INDEX
    Explanations

    complex relationships and interactions within different contexts

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

    Preceding words of comparison

    np_acts-logits-general · gemini-2.0-flash

    such as or like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    tanleria
    -0.60
    ьаж
    -0.54
     disambiguazione
    -0.52
    pherals
    -0.49
     ویکی‌پدیای
    -0.48
    $_['
    -0.48
     kapturem
    -0.47
    IndentedString
    -0.47
    oredCriteria
    -0.46
     Wiktionnaire
    -0.46
    POSITIVE LOGITS
     such
    0.83
     like
    0.78
    such
    0.68
     مثل
    0.56
     takich
    0.55
     seperti
    0.55
     zoals
    0.53
     như
    0.52
     kuten
    0.51
     таких
    0.51
    Activations Density 0.244%

    No Known Activations