© 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. 5040
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "island" 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 @ 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
    PhysRev
    -0.91
     الرياضيه
    -0.82
    nextLine
    -0.69
     Dinamarca
    -0.66
     InputDecoration
    -0.66
     dazu
    -0.66
    TestTools
    -0.65
     Darryl
    -0.65
    Cog
    -0.63
    бяза
    -0.63
    POSITIVE LOGITS
     island
    2.50
     Island
    2.40
    Island
    2.26
    island
    2.21
     islands
    2.18
     ISLAND
    2.14
     Islands
    2.02
    islands
    1.93
    Islands
    1.92
     ISLANDS
    1.65
    Activations Density 0.029%

    No Known Activations