© 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. 10-GEMMASCOPE-RES-16K
    6. 6323
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to chart configuration and manipulation in code

    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
     ſta
    -0.52
    EDEFAULT
    -0.52
    CPtr
    -0.51
     تكبرها
    -0.50
    ChildScrollView
    -0.50
    modelBuilder
    -0.50
    AddTagHelper
    -0.47
     Réponses
    -0.46
    BeginContext
    -0.46
    OGND
    -0.45
    POSITIVE LOGITS
     AssemblyTitle
    0.39
    DotNetBar
    0.39
    akterysty
    0.38
     guste
    0.38
     VIDEOTAPE
    0.37
     glorify
    0.36
     bilgi
    0.33
     تانيه
    0.32
     Reveal
    0.32
     bangsa
    0.32
    Activations Density 0.377%

    No Known Activations