© 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. 16-GEMMASCOPE-RES-16K
    11. 9258
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "After" and phrases related to sequential events or timing

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

    Text following the word "After"

    np_acts-logits-general · gemini-2.0-flash

    After the fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.85
    SBATCH
    -0.84
     ddelweddau
    -0.81
     NUKAT
    -0.80
     esternos
    -0.79
     wikipagina
    -0.78
    principalColumn
    -0.77
    يكب
    -0.77
    XmlAccessType
    -0.76
    Diweddarwch
    -0.76
    POSITIVE LOGITS
     In
    0.67
    In
    0.61
     At
    0.56
    com
    0.55
    cor
    0.51
    ,
    0.50
    +:+
    0.50
    At
    0.50
    ward
    0.47
    Cor
    0.47
    Activations Density 0.269%

    No Known Activations