© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 257
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functions related to Android app development

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

    Android Intents and file operations

    np_acts-logits-general · gemini-2.0-flash

    android intents and system I/O

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -0.82
    tagHelperRunner
    -0.70
    __":
    -0.68
    __":
    -0.68
    +#+#
    -0.67
    mergeFrom
    -0.65
    ()]);
    -0.64
     Chwiliwch
    -0.62
    ništ
    -0.61
    ".
    -0.61
    POSITIVE LOGITS
     يتيمه
    0.71
    BASEPATH
    0.66
    SceneManagement
    0.63
    Przypisy
    0.61
     bpy
    0.61
    krim
    0.56
     Obrador
    0.56
    WireFormatLite
    0.55
     MonoBehaviour
    0.55
    LayoutConstraint
    0.54
    Activations Density 0.220%

    No Known Activations