© 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. 151
    Prev
    Next
    INDEX
    Explanations

    variable and type declarations in code snippets

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

    Strings or code snippets followed by symbols

    np_acts-logits-general · gemini-2.0-flash

    data structure keys and values

    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
     noises
    -0.70
     noise
    -0.63
     sound
    -0.58
    EditorBrowsable
    -0.57
    sound
    -0.54
    noise
    -0.54
     Noise
    -0.53
    Sound
    -0.52
     Sound
    -0.51
     sounds
    -0.50
    POSITIVE LOGITS
     للمعارف
    0.85
     lenker
    0.75
    adaptiveStyles
    0.72
    InputBorder
    0.71
     MainAxisSize
    0.70
     AssemblyCulture
    0.70
    HomeAsUpEnabled
    0.69
     autorytatywna
    0.68
    Kaynakça
    0.67
     SDLK
    0.67
    Activations Density 0.488%

    No Known Activations