© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 96249
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags and their attributes in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    home page or home directory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UnityEditor
    -0.33
     dAtA
    -0.31
    ◀
    -0.30
     Meister
    -0.29
     cuenca
    -0.29
    guantes
    -0.29
    niosek
    -0.29
     tip
    -0.29
     mentira
    -0.29
     particular
    -0.28
    POSITIVE LOGITS
     HomeComponent
    0.94
     HomeController
    0.86
     home
    0.84
    home
    0.81
     homepage
    0.80
     HomeScreen
    0.79
    IntoConstraints
    0.79
    LookAnd
    0.77
    homes
    0.75
     homes
    0.75
    Activations Density 0.014%

    No Known Activations