© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8426
    Prev
    Next
    INDEX
    Explanations

    instances of the word "done" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PathVariable
    -0.83
     gioia
    -0.77
     felicità
    -0.75
    Datuak
    -0.70
     McCarty
    -0.70
     Proctor
    -0.69
    čem
    -0.69
    ibatis
    -0.69
    icoot
    -0.68
     Reif
    -0.67
    POSITIVE LOGITS
    FundMe
    0.92
    eken
    0.88
     seen
    0.88
     Seen
    0.86
    )”.
    0.85
     Donegal
    0.84
     flown
    0.84
     Kuan
    0.83
    )".
    0.81
     PLN
    0.81
    Activations Density 0.107%

    No Known Activations