© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 60956
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "background" in various contexts

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

    background fields and transformations

    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
    SBATCH
    -0.63
     Olli
    -0.52
     Ships
    -0.50
     noDo
    -0.49
    oa̍t
    -0.49
    <bos>
    -0.48
    Ships
    -0.47
     uitges
    -0.47
     Schiffe
    -0.47
    دانشنامهٔ
    -0.45
    POSITIVE LOGITS
     background
    2.23
     Background
    2.03
    Background
    1.94
    background
    1.92
     BACKGROUND
    1.85
    BACKGROUND
    1.63
     backgrounds
    1.60
    背景
    1.49
     Hintergrund
    1.45
     背景
    1.38
    Activations Density 0.011%

    No Known Activations