© 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. 22-GEMMASCOPE-RES-16K
    11. 9555
    Prev
    Next
    INDEX
    Explanations

    verbs related to making or creating change or improvement

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

    Making decisions to improve

    np_acts-logits-general · gemini-2.0-flash

    make decisions or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.74
    EndContext
    -0.65
     disambiguazione
    -0.64
    SourceChecksum
    -0.58
     насељу
    -0.58
    thâu
    -0.58
     defaultstate
    -0.57
    basicConfig
    -0.56
    getColumnIndex
    -0.55
    djangoproject
    -0.55
    POSITIVE LOGITS
     informed
    0.89
     sure
    0.80
     meaningful
    0.74
     Informed
    0.71
    informed
    0.70
     improvements
    0.69
     strides
    0.68
     better
    0.66
     positive
    0.65
     lasting
    0.64
    Activations Density 0.104%

    No Known Activations