© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 615
    Prev
    Next
    INDEX
    Explanations

    configuration parameters and commands related to server setup

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

    server configurations related to SSL settings

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

    network ports and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.83
    énario
    -0.75
    principalTable
    -0.71
    ImageContext
    -0.71
    httphttps
    -0.71
    ²/
    -0.69
    帖最后由
    -0.65
     Administrativna
    -0.64
    الحياه
    -0.63
    ConstraintMaker
    -0.63
    POSITIVE LOGITS
    invokeLater
    0.53
    Mantenimiento
    0.51
    ReusableCell
    0.48
    ArrowToggle
    0.47
    силання
    0.47
     Socialista
    0.44
     lumineuse
    0.44
    водства
    0.44
     eren
    0.42
     PTE
    0.42
    Activations Density 0.008%

    No Known Activations