© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 2197
    Prev
    Next
    INDEX
    Explanations

    instances of the word "learned" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nodoc
    -0.60
    coff
    -0.58
    BoxShadow
    -0.56
    zzleHttp
    -0.55
     Verfügung
    -0.54
     comments
    -0.54
    tuta
    -0.53
     neighbours
    -0.53
    yelitis
    -0.53
    hamb
    -0.52
    POSITIVE LOGITS
     learns
    1.52
     learn
    1.41
     LEARN
    1.40
     learned
    1.37
    learned
    1.37
    learn
    1.34
    Learn
    1.34
    LEARN
    1.33
     Learned
    1.33
     Learn
    1.30
    Activations Density 0.100%

    No Known Activations