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. 16-GEMMASCOPE-RES-16K
    6. 3143
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to API request handling and condition checks

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

    Code that includes boolean logic

    np_acts-logits-general · gemini-2.0-flash

    conditional boolean logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     differ
    -0.57
     Differ
    -0.54
    ieuses
    -0.53
    AddWithValue
    -0.51
    SaveChangesAsync
    -0.50
    onAttach
    -0.50
     RIB
    -0.50
     RouterModule
    -0.49
    তথ্যসূত্র
    -0.48
     onCreateView
    -0.48
    POSITIVE LOGITS
     boolean
    0.84
    boolean
    0.83
    Boolean
    0.81
    bool
    0.79
     bool
    0.79
    BOOLEAN
    0.78
     Boolean
    0.78
    getBoolean
    0.69
    oolean
    0.65
     flag
    0.64
    Activations Density 0.174%

    No Known Activations