© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2545
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal reflection or self-identity

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

    Tokens preceding em-dashes

    np_acts-logits-general · gemini-2.0-flash

    anterior posterior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     â
    -1.73
    â
    -1.63
    Ã
    -1.09
     Â
    -1.08
    Â
    -1.06
     Ã
    -1.02
     ¦
    -0.90
     `
    -0.89
     „
    -0.88
     ð
    -0.84
    POSITIVE LOGITS
    ‐
    1.64
    '
    1.39
    。"
    1.38
    ...'
    1.36
    ："
    1.30
     ​
    1.27
    ​
    1.26
     ‐
    1.26
    ...”
    1.23
    '...
    1.23
    Activations Density 0.604%

    No Known Activations