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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1873
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "not only... but also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.68
     AttributeError
    -0.57
     ModelRenderer
    -0.54
     hoort
    -0.52
     sexe
    -0.50
    yntaxException
    -0.50
     eléctrica
    -0.48
    makeConstraints
    -0.47
    stylers
    -0.47
    CHOICES
    -0.46
    POSITIVE LOGITS
     nejen
    0.54
    不止
    0.51
    不仅
    0.50
    それだけ
    0.49
    不僅
    0.49
    不但
    0.47
    不仅仅
    0.47
    Multiple
    0.45
    owohl
    0.45
     Multiple
    0.43
    Activations Density 0.092%

    No Known Activations