© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10213
    Prev
    Next
    INDEX
    Explanations

    information about increases or changes in various parameters or metrics

    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
     increased
    -0.46
     increasing
    -0.44
    ExecuteReader
    -0.42
     extensive
    -0.40
     EconPapers
    -0.39
    AutoresizingMask
    -0.38
     reduced
    -0.38
    Excess
    -0.38
    뀐
    -0.37
    JNIEnv
    -0.36
    POSITIVE LOGITS
    awareness
    0.73
     awareness
    0.71
     likelihood
    0.65
    opportunities
    0.61
     chances
    0.61
     שוליים
    0.59
     sophistication
    0.59
     scrutiny
    0.58
     dramatically
    0.57
     jumlah
    0.57
    Activations Density 0.478%

    No Known Activations