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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1828
    Prev
    Next
    INDEX
    Explanations

    elements related to navigational components of a webpage, specifically buttons and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {}/
    -0.60
    assination
    -0.56
     soir
    -0.56
    }")
    
    -0.54
    sptr
    -0.53
    ловек
    -0.53
     noqa
    -0.53
    たび
    -0.53
    czaj
    -0.52
    Totale
    -0.52
    POSITIVE LOGITS
     MainAxisSize
    1.06
    ArgsConstructor
    0.84
    TestingModule
    0.76
    dotenv
    0.71
    CardContent
    0.69
    SceneManagement
    0.68
    oa̍t
    0.68
    CppMethod
    0.68
    ViewInit
    0.67
     समीक्षाएं
    0.67
    Activations Density 0.391%

    No Known Activations