© 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. 39-GEMMASCOPE-RES-16K
    6. 3886
    Prev
    Next
    INDEX
    Explanations

    references to efforts or initiatives related to various contexts, particularly emphasizing cooperation and collaboration

    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
     linkovi
    -0.59
    AddTagHelper
    -0.54
    geslacht
    -0.49
    ValueStyle
    -0.48
     doing
    -0.48
    tagHelperRunner
    -0.48
    səhifə
    -0.47
     caneca
    -0.47
    Doing
    -0.46
     pelúcia
    -0.46
    POSITIVE LOGITS
     aimed
    1.02
     undertaken
    0.90
     visant
    0.83
     spearheaded
    0.82
     underway
    0.79
     initiated
    0.75
     involving
    0.75
     aiming
    0.75
     led
    0.74
    initiated
    0.73
    Activations Density 0.757%

    No Known Activations