Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3019
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "El" followed by "Dorado" or other variations, indicating a focus on entities associated with that designation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stappen
    -0.45
     poussière
    -0.44
     assolu
    -0.44
     repuesto
    -0.43
     kysy
    -0.43
     invloed
    -0.43
     fourrure
    -0.43
     Substanz
    -0.42
     voordelen
    -0.42
     arcilla
    -0.42
    POSITIVE LOGITS
     Nio
    0.47
    djangoproject
    0.46
     Wire
    0.45
     estekak
    0.45
     houſe
    0.44
    wood
    0.43
    RTCK
    0.43
     cerv
    0.43
    webElementXpaths
    0.43
    ligibility
    0.41
    Activations Density 0.201%

    No Known Activations