© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5981
    Prev
    Next
    INDEX
    Explanations

    instances of detailed technical analysis or examination of data and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ioutil
    -0.68
    mybatisplus
    -0.64
    جغرافيا
    -0.56
    GEBURTSDATUM
    -0.54
     disambiguazione
    -0.53
    المناصب
    -0.53
    ereço
    -0.53
    cemment
    -0.52
    MessageOf
    -0.52
    andag
    -0.52
    POSITIVE LOGITS
     seems
    3.03
     seem
    3.03
     appears
    2.98
     appear
    2.85
     apparently
    2.81
    seems
    2.78
     seemed
    2.74
     Seems
    2.73
    Seems
    2.69
    seem
    2.66
    Activations Density 1.277%

    No Known Activations