© 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. 4-GEMMASCOPE-RES-16K
    11. 10770
    Prev
    Next
    INDEX
    Explanations

    emphasis on the importance of actions or concepts 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.86
    rungsseite
    -0.69
    :✨
    -0.67
    nthetic
    -0.67
    StoryboardSegue
    -0.63
    \{\\
    -0.59
    COUVER
    -0.58
    \}\\
    -0.58
     genoux
    -0.57
     resourceCulture
    -0.56
    POSITIVE LOGITS
     important
    1.83
     Important
    1.77
    important
    1.69
     importance
    1.68
    Important
    1.62
     Importance
    1.54
    Importance
    1.51
    importance
    1.48
     crucial
    1.44
     penting
    1.43
    Activations Density 0.365%

    No Known Activations