© 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. 15693
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and relationships involving pairs and functions

    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
     [['
    -0.58
    [['
    -0.55
    [_
    -0.47
    Jeografia
    -0.44
    titleMargin
    -0.44
    (\
    -0.44
     desmotivaciones
    -0.44
     ("\
    -0.43
     luy
    -0.43
    centiles
    -0.43
    POSITIVE LOGITS
     $(
    1.51
    $(
    1.33
     }(
    1.19
     }}(
    0.99
    }(
    0.90
    =$(
    0.89
    ($(
    0.81
    }}(
    0.76
    `(
    0.73
    ](
    0.71
    Activations Density 1.689%

    No Known Activations