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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 10151
    Prev
    Next
    INDEX
    Explanations

    HTML form elements related to submission actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.69
     quæ
    -0.69
     ſever
    -0.69
     itſelf
    -0.69
     Inſ
    -0.67
     Houſe
    -0.66
     fevere
    -0.66
     Conſ
    -0.66
    ToMany
    -0.65
     Jefus
    -0.63
    POSITIVE LOGITS
    MigrationBuilder
    0.86
     الحره
    0.83
    /**
    0.74
    WriteBarrier
    0.74
    TextBoxColumn
    0.67
     post
    0.67
     TextStyle
    0.64
     AppCompatTheme
    0.63
    execSQL
    0.63
    TableModel
    0.61
    Activations Density 0.021%

    No Known Activations