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

    Neuronpedia

    Jacobian LensNEW
    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. 15211
    Prev
    Next
    INDEX
    Explanations

    formal mathematical language and structures

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

    Comes after "By the" or "by"

    np_acts-logits-general · gemini-2.0-flash

    By followed by assumption or definition

    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
     Shum
    -0.54
     premia
    -0.52
     Abweich
    -0.52
    Stam
    -0.50
    MigrationBuilder
    -0.49
    AtIndexPath
    -0.49
     deviate
    -0.47
    حياتها
    -0.47
    CppMethod
    -0.46
     Governance
    -0.46
    POSITIVE LOGITS
     definition
    0.72
     Meksiku
    0.64
     theorem
    0.64
    basicConfig
    0.63
     properties
    0.59
    definition
    0.59
    AddHtmlAttribute
    0.58
    saraba
    0.58
     property
    0.57
    Definition
    0.56
    Activations Density 1.106%

    No Known Activations