© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13463
    Prev
    Next
    INDEX
    Explanations

    references to errors or issues in a context, particularly related to responses or programming problems

    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
    -0.49
    :✨
    -0.47
     Exacts
    -0.47
    errHandler
    -0.46
    ☚
    -0.45
    berfläche
    -0.40
    SerializedSize
    -0.39
    exitRule
    -0.38
     noDo
    -0.38
    Географиясе
    -0.38
    POSITIVE LOGITS
     mal
    0.47
     truffles
    0.43
     malen
    0.43
     mals
    0.43
    odios
    0.42
     moles
    0.40
     gaf
    0.40
     tor
    0.39
    openConnection
    0.39
     fasti
    0.38
    Activations Density 0.144%

    No Known Activations