© 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. 8395
    Prev
    Next
    INDEX
    Explanations

    conditional statements and temporal references

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

    that begin conditional clauses

    np_acts-logits-general · gemini-2.0-flash

    pronouns and conditions

    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
    ſelves
    -0.56
    marginVertical
    -0.53
     lowa
    -0.53
    ılmıştır
    -0.52
    .’”
    -0.52
    ='"+
    -0.52
     Sikh
    -0.51
    =$?
    -0.51
    AsyncTask
    -0.50
    ++
    -0.50
    POSITIVE LOGITS
     we
    0.88
     you
    0.83
     they
    0.82
     it
    0.81
     someone
    0.80
     somebody
    0.75
     he
    0.71
    География
    0.70
    someone
    0.66
    AddTagHelper
    0.66
    Activations Density 0.352%

    No Known Activations