© 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. 16-GEMMASCOPE-RES-16K
    11. 13247
    Prev
    Next
    INDEX
    Explanations

    patterns in numeric and character sequences, particularly focusing on identifiers and references

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

    Hexadecimal characters followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings, guids, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.06
     pleaſure
    -1.02
     Majefty
    -0.94
     greateſt
    -0.93
     itſelf
    -0.93
     iſt
    -0.93
     perſon
    -0.92
     ſtate
    -0.91
     Houſe
    -0.91
     houſe
    -0.91
    POSITIVE LOGITS
     po
    0.51
     Ha
    0.48
     Ca
    0.48
     mit
    0.48
     Po
    0.47
     Al
    0.46
     V
    0.44
     P
    0.43
     typelib
    0.43
    \{\\
    0.43
    Activations Density 0.079%

    No Known Activations