© 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. 2792
    Prev
    Next
    INDEX
    Explanations

    phrases related to data entry and processing tasks

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

    Code, non-English, or punctuation

    np_acts-logits-general · gemini-2.0-flash

    railing system, artist Juan, medication assisted

    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
    WithMany
    -0.51
    mongoose
    -0.50
    VIAF
    -0.47
    fjspx
    -0.46
    dinga
    -0.45
    tvguidetime
    -0.43
    lexus
    -0.43
    TagMode
    -0.43
     ce
    -0.42
    JsonIgnore
    -0.40
    POSITIVE LOGITS
     آنجا
    1.05
     allí
    1.04
    在那里
    1.02
     Allí
    0.99
     там
    0.96
     dort
    0.96
     acolo
    0.95
     therein
    0.86
    當地
    0.85
    Там
    0.84
    Activations Density 0.831%

    No Known Activations