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. 12466
    Prev
    Next
    INDEX
    Explanations

    descriptions of quality and durability in products

    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
     يتيمه
    -0.51
    MessageOf
    -0.42
    FlatAppearance
    -0.42
    OGND
    -0.41
    DMETHOD
    -0.40
    が悪い
    -0.40
     jspb
    -0.38
    Eksteraj
    -0.37
     שוליים
    -0.37
    الحياه
    -0.37
    POSITIVE LOGITS
     versatile
    1.17
     sturdy
    1.16
     durable
    1.11
     robust
    0.98
     reliable
    0.94
     dependable
    0.91
    durable
    0.91
     flexible
    0.90
     multifunctional
    0.86
     functional
    0.86
    Activations Density 0.316%

    No Known Activations