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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35172
    Prev
    Next
    INDEX
    Explanations

    mentions of the Android framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Pueden
    -0.24
     ĝ
    -0.23
     voordelen
    -0.20
     Ciò
    -0.20
     głó
    -0.20
     díl
    -0.20
     lze
    -0.19
    Whatever
    -0.19
     adecuadamente
    -0.19
     sebagaimana
    -0.18
    POSITIVE LOGITS
     android
    1.38
     Android
    1.18
    android
    1.10
     يتيمه
    1.07
    Android
    1.03
    ſammen
    1.02
    <unused28>
    1.00
    <unused14>
    0.99
    <unused8>
    0.99
    [@BOS@]
    0.99
    Activations Density 0.001%

    No Known Activations