© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7239
    Prev
    Next
    INDEX
    Explanations

    various technical terms, particularly related to systems and complex structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referrerpolicy
    -0.55
     GenerationType
    -0.54
    uxxxx
    -0.49
     kaarangay
    -0.43
     contextLoads
    -0.41
    setVerticalGroup
    -0.39
    cut
    -0.39
     cut
    -0.37
     shut
    -0.37
    XmlAccessType
    -0.36
    POSITIVE LOGITS
    böz
    0.50
    itinéraire
    0.50
    CppMethod
    0.48
    ßig
    0.48
    styleType
    0.46
    +#+
    0.43
     sahip
    0.42
     تضيفلها
    0.41
     fallu
    0.41
    iksi
    0.40
    Activations Density 1.167%

    No Known Activations