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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7576
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to inequalities and conditions

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

    Mathematical expressions with inequalities

    np_acts-logits-general · gemini-2.0-flash

    comparison operators with numbers

    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
     davon
    -0.69
    ContextHolder
    -0.52
     half
    -0.50
     quanto
    -0.49
     versa
    -0.46
    loginPage
    -0.46
    makeatletter
    -0.44
     rospy
    -0.44
     ")");
    -0.44
    ilares
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.91
     OFDb
    0.66
    EndProject
    0.59
    BindingResult
    0.58
    featureID
    0.58
    enumi
    0.57
    bourhood
    0.56
    PreferredItem
    0.56
     typelib
    0.55
    WarningLevel
    0.54
    Activations Density 0.318%

    No Known Activations