Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15452
    Prev
    Next
    INDEX
    Explanations

    code related to Android Intents and their usage for launching activities and passing data between them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    HandlerContext
    -0.57
     Regan
    -0.52
    ManagedBean
    -0.51
    tableFuture
    -0.46
    Initializable
    -0.45
     no
    -0.45
    geno
    -0.45
     ach
    -0.44
     na
    -0.44
    Slf
    -0.43
    POSITIVE LOGITS
    uxxxx
    0.82
     ContentValues
    0.80
     Roskov
    0.79
    abestanden
    0.76
     الحره
    0.76
     BoxDecoration
    0.74
     ſtate
    0.73
     Khart
    0.71
     Stande
    0.69
    новниш
    0.68
    Activations Density 0.256%

    No Known Activations