© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 1605
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" and its variations, indicating a focus on comparative quantity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ️
    -0.83
    Personensuche
    -0.83
    (&:
    -0.79
    IndentedString
    -0.76
    bufio
    -0.72
    middels
    -0.70
    GetAxis
    -0.68
     Cæsar
    -0.67
    OGND
    -0.67
    styrelsen
    -0.67
    POSITIVE LOGITS
     than
    1.31
    than
    0.86
     THAN
    0.83
    Than
    0.82
     niż
    0.81
     Than
    0.80
     MORE
    0.73
     než
    0.73
     Moreno
    0.73
     Moreira
    0.72
    Activations Density 0.165%

    No Known Activations