© 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. 7-GEMMASCOPE-RES-16K
    6. 11907
    Prev
    Next
    INDEX
    Explanations

    references to "first" 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 @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     méri
    -0.99
     Scrolls
    -0.90
     mourut
    -0.89
    ukone
    -0.89
     decorada
    -0.89
     régl
    -0.85
     specchio
    -0.84
     Krieger
    -0.83
     écl
    -0.83
     Tales
    -0.83
    POSITIVE LOGITS
     First
    1.79
    FIRST
    1.75
     FIRST
    1.67
    First
    1.65
     first
    1.64
    first
    1.50
     first
    1.22
     getFirst
    1.21
     ersten
    1.17
    第一
    1.11
    Activations Density 0.156%

    No Known Activations