© 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. 7841
    Prev
    Next
    INDEX
    Explanations

    specific programming or scripting terms related to coding contexts

    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
    ltä
    -1.42
     británico
    -1.05
     brasileño
    -1.02
     Atlántico
    -1.02
    yttä
    -1.02
    ntä
    -1.00
     Asamblea
    -0.98
    isiä
    -0.98
    vägen
    -0.98
     Espíritu
    -0.96
    POSITIVE LOGITS
     um
    0.65
     inse
    0.64
     $_(
    0.63
     dita
    0.63
     gover
    0.63
     por
    0.62
     encre
    0.62
     $_"
    0.62
     seq
    0.61
     sess
    0.61
    Activations Density 0.354%

    No Known Activations