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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8861
    Prev
    Next
    INDEX
    Explanations

    non-standard words or phrases with significant symbolic or cultural references

    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
     propOrder
    -0.60
     étoit
    -0.58
    HomeAsUpEnabled
    -0.57
    drawSprites
    -0.55
     inalámb
    -0.54
     femininos
    -0.53
     engraçadas
    -0.53
    UserScript
    -0.52
    нгред
    -0.51
     avoient
    -0.51
    POSITIVE LOGITS
    <unused63>
    0.71
    <unused60>
    0.71
    <unused61>
    0.63
    <unused62>
    0.61
    uxxxx
    0.59
    ​​
    0.53
    <eos>
    0.53
    ­
    0.52
    TRIBUN
    0.51
    ​​​
    0.45
    Activations Density 1.438%

    No Known Activations