© 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. 3-GEMMASCOPE-RES-16K
    6. 8088
    Prev
    Next
    INDEX
    Explanations

    specific measurements and descriptors related to nanotechnology and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ciencias
    -0.31
     Sélection
    -0.31
     layui
    -0.30
     Senado
    -0.30
     invention
    -0.29
     fittest
    -0.29
     Hens
    -0.28
     gelas
    -0.28
    proxies
    -0.27
    不愧
    -0.27
    POSITIVE LOGITS
    AddTagHelper
    0.92
    nm
    0.74
    Cyfarwyddwr
    0.73
     kasarigan
    0.71
    Amb
    0.70
     Amb
    0.66
     amb
    0.64
    amb
    0.63
    angliski
    0.62
    tagHelperRunner
    0.61
    Activations Density 1.478%

    No Known Activations