© 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. 10356
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical codes or patterns within the text

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

    Hexadecimal representations of characters

    np_acts-logits-general · gemini-2.0-flash

    unicode escape sequences

    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
    IUrlHelper
    -0.87
    awtextra
    -0.84
     odkazy
    -0.82
    expandindo
    -0.78
     '{@
    -0.77
    SourceChecksum
    -0.76
    AntiForgeryToken
    -0.76
     متعلقه
    -0.75
     autorytatywna
    -0.74
     MotionEvent
    -0.73
    POSITIVE LOGITS
    )};
    0.41
    castle
    0.41
    }})
    0.40
     poliuret
    0.40
    eda
    0.39
    '));
    0.39
    Igual
    0.38
    wendige
    0.38
    "+
    0.38
    ="">
    0.37
    Activations Density 0.495%

    No Known Activations