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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 30519
    Prev
    Next
    INDEX
    Explanations

    elements related to image and view components in Android development

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

    UI image views

    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
     trilha
    -0.43
     campionato
    -0.38
     garansi
    -0.37
     teratur
    -0.37
     bankası
    -0.37
    JMenu
    -0.36
     huelga
    -0.36
     soluções
    -0.36
     ziyaretçi
    -0.36
     cordones
    -0.36
    POSITIVE LOGITS
     UIImageView
    1.02
    PictureBox
    0.88
    UIImageView
    0.87
     ImageView
    0.79
    ImageView
    0.78
     pictureBox
    0.73
     imageView
    0.68
     createSprite
    0.63
    RenderAtEndOf
    0.63
    picasso
    0.62
    Activations Density 0.008%

    No Known Activations