© 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. 7580
    Prev
    Next
    INDEX
    Explanations

    terms related to probabilities and statistics, especially in the context of sampling without replacement

    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
    AnchorTagHelper
    -0.43
    ::_('
    -0.43
    |]
    -0.41
    ]=>
    -0.40
    IndentedString
    -0.39
    PageRoute
    -0.38
    letoe
    -0.37
     tartalomajánló
    -0.37
    ötzlich
    -0.36
    SerializedSize
    -0.36
    POSITIVE LOGITS
     without
    4.22
    without
    3.73
     Without
    3.59
    Without
    3.55
     zonder
    3.22
     ohne
    3.19
     tanpa
    3.14
     WITHOUT
    3.14
     без
    3.13
     senza
    2.97
    Activations Density 4.079%

    No Known Activations