© 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. 2-GEMMASCOPE-RES-16K
    6. 1882
    Prev
    Next
    INDEX
    Explanations

    the word "then" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.71
     Jefus
    -0.71
     ſtate
    -0.70
    rawDesc
    -0.69
     houſe
    -0.68
     Diſ
    -0.68
    ('/:
    -0.68
     Majefty
    -0.67
     preſent
    -0.65
     Allegretto
    -0.65
    POSITIVE LOGITS
     puis
    0.69
     “
    0.57
     or
    0.56
     ComVisible
    0.55
     But
    0.55
     ثم
    0.55
     but
    0.55
    modelBuilder
    0.53
    然后再
    0.52
    “
    0.52
    Activations Density 0.170%

    No Known Activations