© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14819
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'X' in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kör
    -0.30
    IActionResult
    -0.30
     measure
    -0.28
     mittel
    -0.27
     Darauf
    -0.26
     mesure
    -0.25
    PROPOSED
    -0.25
     geçmiş
    -0.25
     dwell
    -0.25
    Distribuzione
    -0.25
    POSITIVE LOGITS
    ValueStyle
    0.65
    tend
    0.64
     EconPapers
    0.64
    탤
    0.62
    SourceChecksum
    0.62
    CppMethod
    0.60
     wireType
    0.58
    رشف
    0.57
    ruptedException
    0.57
     Taktlose
    0.57
    Activations Density 0.463%

    No Known Activations