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

    Neuronpedia

    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. 1980
    Prev
    Next
    INDEX
    Explanations

    code patterns and control flow structures

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

    Code, especially class/function definitions and conditional statements

    np_acts-logits-general · gemini-2.0-flash

    python function and class definitions

    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
    ibouti
    -0.49
    \%
    -0.48
    цездатний
    -0.47
    ernoo
    -0.47
    はいけない
    -0.45
    सन्दर्भ
    -0.44
    ļu
    -0.44
     końcu
    -0.44
    になれる
    -0.43
     andet
    -0.43
    POSITIVE LOGITS
     __
    0.91
     CascadeType
    0.88
     FetchType
    0.73
    TagHelpers
    0.67
    BeginInit
    0.67
     NSCoder
    0.63
    iffance
    0.63
     OnInit
    0.62
    interopRequire
    0.62
    .__
    0.61
    Activations Density 0.076%

    No Known Activations