© 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. 18-GEMMASCOPE-RES-16K
    11. 1764
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

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

    "0" after numbers

    np_acts-logits-general · gemini-2.0-flash

    dates with month names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /***/
    -0.50
     rivel
    -0.50
    }}}\
    -0.47
     Emits
    -0.47
     joten
    -0.46
    šanu
    -0.46
     nudo
    -0.45
    ään
    -0.45
     længere
    -0.45
    MessageTagHelper
    -0.44
    POSITIVE LOGITS
    +#+#
    0.85
     متعلقه
    0.77
    ThroughAttribute
    0.74
    ReusableCell
    0.68
    SourceChecksum
    0.64
    RegressionTest
    0.64
    ItemBackground
    0.64
    tagHelperRunner
    0.60
    SequentialGroup
    0.58
     next
    0.56
    Activations Density 0.522%

    No Known Activations