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. 35-GEMMASCOPE-RES-16K
    6. 12555
    Prev
    Next
    INDEX
    Explanations

    structured scientific terms and equations related to gauge theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ️
    -0.54
    triangleq
    -0.52
    ∅
    -0.48
     lode
    -0.48
    \{\\
    -0.47
     насељу
    -0.47
    BindingSource
    -0.47
    HttpSession
    -0.44
    ≜
    -0.44
     ‹
    -0.43
    POSITIVE LOGITS
     manifestly
    0.52
     explí
    0.50
     renon
    0.50
    новниш
    0.46
     explicitly
    0.46
     flavour
    0.46
     PHYSICAL
    0.45
     trilha
    0.45
     noDo
    0.45
     smeared
    0.45
    Activations Density 3.444%

    No Known Activations