© 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. 3687
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "instructions" 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 @ 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
     harem
    -0.81
     Neve
    -0.80
     Nema
    -0.79
     Gaps
    -0.78
     GAP
    -0.77
     Nemesis
    -0.76
     Kuz
    -0.76
     كومونز
    -0.75
    Kuz
    -0.74
    ponses
    -0.74
    POSITIVE LOGITS
     instructions
    2.65
     Instructions
    2.37
     instruction
    2.33
    instructions
    2.17
    Instructions
    2.13
     Instruction
    2.08
     instruct
    1.95
     instructed
    1.95
     INSTRUCTIONS
    1.93
    Instruction
    1.91
    Activations Density 0.075%

    No Known Activations