© 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. 5-GEMMASCOPE-RES-16K
    11. 6879
    Prev
    Next
    INDEX
    Explanations

    references to animated shows and cartoons, particularly those involving violence and adventure themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderSide
    -0.55
     blessé
    -0.52
    ParallelGroup
    -0.51
    cshtml
    -0.49
    EntityFramework
    -0.49
    SqlClient
    -0.49
     coû
    -0.49
    Przeczytaj
    -0.47
    PackageManager
    -0.47
     pouvons
    -0.45
    POSITIVE LOGITS
     cartoon
    1.08
     cartoons
    1.07
     animation
    0.96
     animated
    0.92
     مرئيه
    0.88
    Cartoon
    0.85
     Animation
    0.85
     Cartoon
    0.85
     anim
    0.81
     kartun
    0.81
    Activations Density 0.452%

    No Known Activations