© 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. 22-GEMMASCOPE-RES-16K
    11. 3539
    Prev
    Next
    INDEX
    Explanations

    references to the term "Sim" and its variations, indicating a focus on simulations or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens starting with "Sim"

    np_acts-logits-general · gemini-2.0-flash

    simulations, simpler, similarities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.90
    Spoljašnje
    -0.79
     onCreateView
    -0.78
     jsPsych
    -0.74
    transQ
    -0.68
    hearsed
    -0.64
    PerformLayout
    -0.62
    }")]
    -0.60
     ͡°)
    -0.60
    ]";
    -0.60
    POSITIVE LOGITS
    vastatin
    0.66
     annealing
    0.66
     SIM
    0.65
     sims
    0.60
    Sim
    0.59
    Sims
    0.58
    sim
    0.57
     Sim
    0.56
     Sims
    0.54
     sim
    0.54
    Activations Density 0.079%

    No Known Activations