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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11365
    Prev
    Next
    INDEX
    Explanations

    comments and documentation related to code functions and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.79
    AddTagHelper
    -0.78
     nakalista
    -0.75
    verifyException
    -0.74
    تقاوى
    -0.65
     unknownFields
    -0.65
    RegressionTest
    -0.63
    transQ
    -0.63
    principalTable
    -0.62
    Portály
    -0.62
    POSITIVE LOGITS
     used
    0.54
    用来
    0.52
     This
    0.50
     Used
    0.49
    用于
    0.47
     provides
    0.47
     helper
    0.47
     pozwala
    0.46
     fornece
    0.46
     hjelpe
    0.45
    Activations Density 0.354%

    No Known Activations