Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13370
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Fre" in relation to a context involving percentages or frequency

    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
     lateinit
    -0.54
     AspNetCore
    -0.54
    ACHUSET
    -0.52
    تقاوى
    -0.49
    RegressionTest
    -0.48
    /**
    -0.46
    ViewImports
    -0.46
    +:+
    -0.46
     defaultstate
    -0.45
     AssemblyTitle
    -0.44
    POSITIVE LOGITS
    Fre
    0.84
     Fre
    0.81
     fre
    0.78
     FRE
    0.65
     Freem
    0.62
    fre
    0.58
    FRE
    0.55
     Freeman
    0.48
     Fremont
    0.47
    Freeman
    0.44
    Activations Density 0.403%

    No Known Activations